Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods
This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampl...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Borges, Tomé Almeida [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2020transfer abstract |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: Atomic collapse in graphene quantum dots in a magnetic field - Eren, I. ELSEVIER, 2022, the official journal of the World Federation on Soft Computing (WFSC), Amsterdam [u.a.] |
|---|---|
| Übergeordnetes Werk: |
volume:90 ; year:2020 ; pages:0 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.asoc.2020.106187 |
|---|
| Katalog-ID: |
ELV050045164 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV050045164 | ||
| 003 | DE-627 | ||
| 005 | 20230626025703.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 200518s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.asoc.2020.106187 |2 doi | |
| 028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000000981.pica |
| 035 | |a (DE-627)ELV050045164 | ||
| 035 | |a (ELSEVIER)S1568-4946(20)30127-7 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 540 |a 530 |q VZ |
| 084 | |a 33.00 |2 bkl | ||
| 100 | 1 | |a Borges, Tomé Almeida |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods |
| 264 | 1 | |c 2020transfer abstract | |
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. | ||
| 520 | |a This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. | ||
| 650 | 7 | |a Cryptocurrencies |2 Elsevier | |
| 650 | 7 | |a Technical analysis |2 Elsevier | |
| 650 | 7 | |a Financial markets |2 Elsevier | |
| 650 | 7 | |a Financial data resampling |2 Elsevier | |
| 650 | 7 | |a Machine learning |2 Elsevier | |
| 650 | 7 | |a Ensemble classification |2 Elsevier | |
| 700 | 1 | |a Neves, Rui Ferreira |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier Science |a Eren, I. ELSEVIER |t Atomic collapse in graphene quantum dots in a magnetic field |d 2022 |d the official journal of the World Federation on Soft Computing (WFSC) |g Amsterdam [u.a.] |w (DE-627)ELV007866305 |
| 773 | 1 | 8 | |g volume:90 |g year:2020 |g pages:0 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.asoc.2020.106187 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 936 | b | k | |a 33.00 |j Physik: Allgemeines |q VZ |
| 951 | |a AR | ||
| 952 | |d 90 |j 2020 |h 0 | ||
| author_variant |
t a b ta tab |
|---|---|
| matchkey_str |
borgestomalmeidanevesruiferreira:2020----:nebefahnlannagrtmfrrpournynetetihifr |
| hierarchy_sort_str |
2020transfer abstract |
| bklnumber |
33.00 |
| publishDate |
2020 |
| allfields |
10.1016/j.asoc.2020.106187 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000000981.pica (DE-627)ELV050045164 (ELSEVIER)S1568-4946(20)30127-7 DE-627 ger DE-627 rakwb eng 540 530 VZ 33.00 bkl Borges, Tomé Almeida verfasserin aut Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods 2020transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. Cryptocurrencies Elsevier Technical analysis Elsevier Financial markets Elsevier Financial data resampling Elsevier Machine learning Elsevier Ensemble classification Elsevier Neves, Rui Ferreira oth Enthalten in Elsevier Science Eren, I. ELSEVIER Atomic collapse in graphene quantum dots in a magnetic field 2022 the official journal of the World Federation on Soft Computing (WFSC) Amsterdam [u.a.] (DE-627)ELV007866305 volume:90 year:2020 pages:0 https://doi.org/10.1016/j.asoc.2020.106187 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U 33.00 Physik: Allgemeines VZ AR 90 2020 0 |
| spelling |
10.1016/j.asoc.2020.106187 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000000981.pica (DE-627)ELV050045164 (ELSEVIER)S1568-4946(20)30127-7 DE-627 ger DE-627 rakwb eng 540 530 VZ 33.00 bkl Borges, Tomé Almeida verfasserin aut Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods 2020transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. Cryptocurrencies Elsevier Technical analysis Elsevier Financial markets Elsevier Financial data resampling Elsevier Machine learning Elsevier Ensemble classification Elsevier Neves, Rui Ferreira oth Enthalten in Elsevier Science Eren, I. ELSEVIER Atomic collapse in graphene quantum dots in a magnetic field 2022 the official journal of the World Federation on Soft Computing (WFSC) Amsterdam [u.a.] (DE-627)ELV007866305 volume:90 year:2020 pages:0 https://doi.org/10.1016/j.asoc.2020.106187 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U 33.00 Physik: Allgemeines VZ AR 90 2020 0 |
| allfields_unstemmed |
10.1016/j.asoc.2020.106187 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000000981.pica (DE-627)ELV050045164 (ELSEVIER)S1568-4946(20)30127-7 DE-627 ger DE-627 rakwb eng 540 530 VZ 33.00 bkl Borges, Tomé Almeida verfasserin aut Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods 2020transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. Cryptocurrencies Elsevier Technical analysis Elsevier Financial markets Elsevier Financial data resampling Elsevier Machine learning Elsevier Ensemble classification Elsevier Neves, Rui Ferreira oth Enthalten in Elsevier Science Eren, I. ELSEVIER Atomic collapse in graphene quantum dots in a magnetic field 2022 the official journal of the World Federation on Soft Computing (WFSC) Amsterdam [u.a.] (DE-627)ELV007866305 volume:90 year:2020 pages:0 https://doi.org/10.1016/j.asoc.2020.106187 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U 33.00 Physik: Allgemeines VZ AR 90 2020 0 |
| allfieldsGer |
10.1016/j.asoc.2020.106187 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000000981.pica (DE-627)ELV050045164 (ELSEVIER)S1568-4946(20)30127-7 DE-627 ger DE-627 rakwb eng 540 530 VZ 33.00 bkl Borges, Tomé Almeida verfasserin aut Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods 2020transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. Cryptocurrencies Elsevier Technical analysis Elsevier Financial markets Elsevier Financial data resampling Elsevier Machine learning Elsevier Ensemble classification Elsevier Neves, Rui Ferreira oth Enthalten in Elsevier Science Eren, I. ELSEVIER Atomic collapse in graphene quantum dots in a magnetic field 2022 the official journal of the World Federation on Soft Computing (WFSC) Amsterdam [u.a.] (DE-627)ELV007866305 volume:90 year:2020 pages:0 https://doi.org/10.1016/j.asoc.2020.106187 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U 33.00 Physik: Allgemeines VZ AR 90 2020 0 |
| allfieldsSound |
10.1016/j.asoc.2020.106187 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000000981.pica (DE-627)ELV050045164 (ELSEVIER)S1568-4946(20)30127-7 DE-627 ger DE-627 rakwb eng 540 530 VZ 33.00 bkl Borges, Tomé Almeida verfasserin aut Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods 2020transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. Cryptocurrencies Elsevier Technical analysis Elsevier Financial markets Elsevier Financial data resampling Elsevier Machine learning Elsevier Ensemble classification Elsevier Neves, Rui Ferreira oth Enthalten in Elsevier Science Eren, I. ELSEVIER Atomic collapse in graphene quantum dots in a magnetic field 2022 the official journal of the World Federation on Soft Computing (WFSC) Amsterdam [u.a.] (DE-627)ELV007866305 volume:90 year:2020 pages:0 https://doi.org/10.1016/j.asoc.2020.106187 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U 33.00 Physik: Allgemeines VZ AR 90 2020 0 |
| language |
English |
| source |
Enthalten in Atomic collapse in graphene quantum dots in a magnetic field Amsterdam [u.a.] volume:90 year:2020 pages:0 |
| sourceStr |
Enthalten in Atomic collapse in graphene quantum dots in a magnetic field Amsterdam [u.a.] volume:90 year:2020 pages:0 |
| format_phy_str_mv |
Article |
| bklname |
Physik: Allgemeines |
| institution |
findex.gbv.de |
| topic_facet |
Cryptocurrencies Technical analysis Financial markets Financial data resampling Machine learning Ensemble classification |
| dewey-raw |
540 |
| isfreeaccess_bool |
false |
| container_title |
Atomic collapse in graphene quantum dots in a magnetic field |
| authorswithroles_txt_mv |
Borges, Tomé Almeida @@aut@@ Neves, Rui Ferreira @@oth@@ |
| publishDateDaySort_date |
2020-01-01T00:00:00Z |
| hierarchy_top_id |
ELV007866305 |
| dewey-sort |
3540 |
| id |
ELV050045164 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV050045164</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626025703.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">200518s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.asoc.2020.106187</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000000981.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV050045164</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1568-4946(20)30127-7</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">540</subfield><subfield code="a">530</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">33.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Borges, Tomé Almeida</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Cryptocurrencies</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Technical analysis</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Financial markets</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Financial data resampling</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Machine learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Ensemble classification</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Neves, Rui Ferreira</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Eren, I. ELSEVIER</subfield><subfield code="t">Atomic collapse in graphene quantum dots in a magnetic field</subfield><subfield code="d">2022</subfield><subfield code="d">the official journal of the World Federation on Soft Computing (WFSC)</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV007866305</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:90</subfield><subfield code="g">year:2020</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.asoc.2020.106187</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">33.00</subfield><subfield code="j">Physik: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">90</subfield><subfield code="j">2020</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| author |
Borges, Tomé Almeida |
| spellingShingle |
Borges, Tomé Almeida ddc 540 bkl 33.00 Elsevier Cryptocurrencies Elsevier Technical analysis Elsevier Financial markets Elsevier Financial data resampling Elsevier Machine learning Elsevier Ensemble classification Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods |
| authorStr |
Borges, Tomé Almeida |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV007866305 |
| format |
electronic Article |
| dewey-ones |
540 - Chemistry & allied sciences 530 - Physics |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
540 530 VZ 33.00 bkl Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods Cryptocurrencies Elsevier Technical analysis Elsevier Financial markets Elsevier Financial data resampling Elsevier Machine learning Elsevier Ensemble classification Elsevier |
| topic |
ddc 540 bkl 33.00 Elsevier Cryptocurrencies Elsevier Technical analysis Elsevier Financial markets Elsevier Financial data resampling Elsevier Machine learning Elsevier Ensemble classification |
| topic_unstemmed |
ddc 540 bkl 33.00 Elsevier Cryptocurrencies Elsevier Technical analysis Elsevier Financial markets Elsevier Financial data resampling Elsevier Machine learning Elsevier Ensemble classification |
| topic_browse |
ddc 540 bkl 33.00 Elsevier Cryptocurrencies Elsevier Technical analysis Elsevier Financial markets Elsevier Financial data resampling Elsevier Machine learning Elsevier Ensemble classification |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
r f n rf rfn |
| hierarchy_parent_title |
Atomic collapse in graphene quantum dots in a magnetic field |
| hierarchy_parent_id |
ELV007866305 |
| dewey-tens |
540 - Chemistry 530 - Physics |
| hierarchy_top_title |
Atomic collapse in graphene quantum dots in a magnetic field |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV007866305 |
| title |
Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods |
| ctrlnum |
(DE-627)ELV050045164 (ELSEVIER)S1568-4946(20)30127-7 |
| title_full |
Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods |
| author_sort |
Borges, Tomé Almeida |
| journal |
Atomic collapse in graphene quantum dots in a magnetic field |
| journalStr |
Atomic collapse in graphene quantum dots in a magnetic field |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
500 - Science |
| recordtype |
marc |
| publishDateSort |
2020 |
| contenttype_str_mv |
zzz |
| container_start_page |
0 |
| author_browse |
Borges, Tomé Almeida |
| container_volume |
90 |
| class |
540 530 VZ 33.00 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Borges, Tomé Almeida |
| doi_str_mv |
10.1016/j.asoc.2020.106187 |
| dewey-full |
540 530 |
| title_sort |
ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods |
| title_auth |
Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods |
| abstract |
This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. |
| abstractGer |
This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. |
| abstract_unstemmed |
This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U |
| title_short |
Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods |
| url |
https://doi.org/10.1016/j.asoc.2020.106187 |
| remote_bool |
true |
| author2 |
Neves, Rui Ferreira |
| author2Str |
Neves, Rui Ferreira |
| ppnlink |
ELV007866305 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth |
| doi_str |
10.1016/j.asoc.2020.106187 |
| up_date |
2024-07-06T23:14:43.125Z |
| _version_ |
1803873349142577152 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV050045164</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626025703.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">200518s2020 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.asoc.2020.106187</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000000981.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV050045164</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1568-4946(20)30127-7</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">540</subfield><subfield code="a">530</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">33.00</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Borges, Tomé Almeida</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Ensemble of machine learning algorithms for cryptocurrency investment with different data resampling methods</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">This work proposes a system based on machine learning aimed at creating an investment strategy capable of trading on the cryptocurrency exchange markets. Additionally, with the goal of generating investments with higher returns and lower risk, rather than investing on predictions based on time sampled financial series, a novel method for resampling financial series was developed and employed in this work. For this purpose, the originally time sampled financial series are resampled according to a closing value threshold, thus creating a series prone to obtaining higher returns and lower risk than the original series. Out of these resampled series as well as the original, technical indicators are calculated and fed as inputs to four machine learning algorithms: Logistic Regression, Random Forest, Support Vector Classifier, and Gradient Tree Boosting. Each of these algorithms is responsible for generating a transaction signal. Afterwards, a fifth transaction signal is generated by simply calculating the unweighted average of the four trading signals outputted from the previous algorithms, to improve on their results. In the end, the investment results obtained with the resampled series are compared to the commonly utilized fixed time interval sampling. This work demonstrates that independently of using or not a resampling method, all learning algorithms outperform the Buy and Hold (B&H) strategy in the overwhelming majority of the 100 markets tested. Nevertheless, out of the learning algorithms, the unweighted average obtains the best overall results, namely accuracies up to 59.26% for time resampled series. But most importantly, it is concluded that both alternative resampling methods tested are capable of generating far greater returns and with lower risk relatively to time resampled data.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Cryptocurrencies</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Technical analysis</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Financial markets</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Financial data resampling</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Machine learning</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Ensemble classification</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Neves, Rui Ferreira</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science</subfield><subfield code="a">Eren, I. ELSEVIER</subfield><subfield code="t">Atomic collapse in graphene quantum dots in a magnetic field</subfield><subfield code="d">2022</subfield><subfield code="d">the official journal of the World Federation on Soft Computing (WFSC)</subfield><subfield code="g">Amsterdam [u.a.]</subfield><subfield code="w">(DE-627)ELV007866305</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:90</subfield><subfield code="g">year:2020</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.asoc.2020.106187</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">33.00</subfield><subfield code="j">Physik: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">90</subfield><subfield code="j">2020</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| score |
7.4027634 |