SISTEM ZA UPRAVLJANJE ŽALBAMA KORISNIKA U DOMENU FINANSIJA
Ključne reči:
određivanje sentimenta, klasifikacija žalbe, rad sa velikom količinom podataka, distribuirano okruženje
Apstrakt
U radu je predstavljen sistem za upravljanje žalbama korisnika u domenu finansija. Sistem je zasnovan nad velikim brojem realnih žalbi sa ciljem da kompaniji pruži mogućnost automatskog upravljanja žalbama, tako što će u realnom vremenu vršiti predikcije koje rešene žalbe ne zadovoljavaju korisnike koji su ih uložili i koji je očekivani broj žalbi za naredni mesec. Krajnji cilj ovog sistema jeste smanjenje broja nezadovoljnih korisnika date kompanije. Zbog rada sa velikom količinom podataka, ceo sistem odvija se u distribuiranom okruženju.
Reference
[1]https://www.consumerfinance.gov/data-research/consumer-complaints/ [pristupljeno 16.7.2019.]
[2]https://hadoop.apache.org/ [pristupljeno 15.7.2019.]
[3]https://spark.apache.org/ [pristupljeno 15.7.2019.]
[4]https://restfulapi.net/ [pristupljeno 16.7.2019.]
[5]https://angular.io/ [pristupljeno 16.7.2019.]
[6]https://dev.socrata.com/foundry/data.consumerfinance.gov/s6ew-h6mp [pristupljeno 16.7.2019.]
[7]https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LinearRegression.html [pristupljeno 16.7.2019.]
[8]https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.LabelEncoder.html [pristupljeno 15.7.2019.]
[9]Clayton J. Hutto / Eric Gilbert, Vader: A parsimonious rule-based model for sentiment analysis of social media text, In: Eighth international AAAI conference on weblogs and social media, 2014.
[10]https://imbalanced-learn.readthedocs.io/en/stable/generated/imblearn.over_sampling.SMOTE.html [pristupljeno 16.7.2019.]
[11]https://xgboost.readthedocs.io/en/latest/ [pristupljeno 16.7.2019.]
[12]https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.RandomizedSearchCV.html [pristupljeno 16.7.2019.]
[13]https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html [pristupljeno 16.7.2019.]
[14]Jacob Devlin et al, Bert: Pre-training of deep bidirectional transformers for language understanding, arXiv preprint arXiv:1810.04805, 2018.
[2]https://hadoop.apache.org/ [pristupljeno 15.7.2019.]
[3]https://spark.apache.org/ [pristupljeno 15.7.2019.]
[4]https://restfulapi.net/ [pristupljeno 16.7.2019.]
[5]https://angular.io/ [pristupljeno 16.7.2019.]
[6]https://dev.socrata.com/foundry/data.consumerfinance.gov/s6ew-h6mp [pristupljeno 16.7.2019.]
[7]https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LinearRegression.html [pristupljeno 16.7.2019.]
[8]https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.LabelEncoder.html [pristupljeno 15.7.2019.]
[9]Clayton J. Hutto / Eric Gilbert, Vader: A parsimonious rule-based model for sentiment analysis of social media text, In: Eighth international AAAI conference on weblogs and social media, 2014.
[10]https://imbalanced-learn.readthedocs.io/en/stable/generated/imblearn.over_sampling.SMOTE.html [pristupljeno 16.7.2019.]
[11]https://xgboost.readthedocs.io/en/latest/ [pristupljeno 16.7.2019.]
[12]https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.RandomizedSearchCV.html [pristupljeno 16.7.2019.]
[13]https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html [pristupljeno 16.7.2019.]
[14]Jacob Devlin et al, Bert: Pre-training of deep bidirectional transformers for language understanding, arXiv preprint arXiv:1810.04805, 2018.
Objavljeno
2019-11-06
Sekcija
Elektrotehničko i računarsko inženjerstvo
