Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Selecting the best model for predicting a term deposit product take-up in banking
In this study, we use data mining techniques to build predictive models on data collected by a Portuguese bank through a term savings product campaign conducted between May 2008 and November 2010. This data is imbalanced, given an observed take-up rate of 11.27%. Ling et al. (1998) indicated that...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Statistical Sciences
2019
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613142817701888 |
|---|---|
| access_status_str | Open Access |
| author | Hlongwane, Rivalani Willie |
| author2 | Rajaratnam, Kanshukan |
| author_browse | Hlongwane, Rivalani Willie Rajaratnam, Kanshukan |
| author_facet | Rajaratnam, Kanshukan Hlongwane, Rivalani Willie |
| author_sort | Hlongwane, Rivalani Willie |
| collection | Thesis |
| description | In this study, we use data mining techniques to build predictive models on data collected by a Portuguese bank through a term savings product campaign conducted between May 2008 and November 2010. This data is imbalanced, given an observed take-up rate of 11.27%. Ling et al. (1998) indicated that predictive models built on imbalanced data tend to yield low sensitivity and high specificity, an indication of low true positive and high true negative rates. Our study confirms this finding. We, therefore, use three sampling techniques, namely, under-sampling, oversampling and Synthetic Minority Over-sampling Technique, to balance the data, this results in three additional datasets to use for modelling. We build the following predictive models: random forest, multivariate adaptive regression splines, neural network and support vector machine on the datasets and we compare the models against each other for their ability to identify customers that are likely to take-up a term savings product. As part of the model building process, we investigate parameter permutations related to each modelling technique to tune the models, we find that this assists in building robust models. We assess our models for predictive performance through the use of the receiver operating characteristic curve, confusion matrix, GINI, kappa, sensitivity, specificity, and lift and gains charts. A multivariate adaptive regression splines model built on over-sampled data is found to be the best model for predicting term savings product takeup. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/29789 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:31:26.417Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2019 |
| publishDateRange | 2019 |
| publishDateSort | 2019 |
| publisher | Department of Statistical Sciences |
| publisherStr | Department of Statistical Sciences |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/29789 Selecting the best model for predicting a term deposit product take-up in banking Hlongwane, Rivalani Willie Rajaratnam, Kanshukan Huang, Chun-Kai Statistical Science data mining financial predictive models In this study, we use data mining techniques to build predictive models on data collected by a Portuguese bank through a term savings product campaign conducted between May 2008 and November 2010. This data is imbalanced, given an observed take-up rate of 11.27%. Ling et al. (1998) indicated that predictive models built on imbalanced data tend to yield low sensitivity and high specificity, an indication of low true positive and high true negative rates. Our study confirms this finding. We, therefore, use three sampling techniques, namely, under-sampling, oversampling and Synthetic Minority Over-sampling Technique, to balance the data, this results in three additional datasets to use for modelling. We build the following predictive models: random forest, multivariate adaptive regression splines, neural network and support vector machine on the datasets and we compare the models against each other for their ability to identify customers that are likely to take-up a term savings product. As part of the model building process, we investigate parameter permutations related to each modelling technique to tune the models, we find that this assists in building robust models. We assess our models for predictive performance through the use of the receiver operating characteristic curve, confusion matrix, GINI, kappa, sensitivity, specificity, and lift and gains charts. A multivariate adaptive regression splines model built on over-sampled data is found to be the best model for predicting term savings product takeup. 2019-02-22T12:07:13Z 2019-02-22T12:07:13Z 2018 2019-02-19T06:40:45Z Master Thesis Masters MSc http://hdl.handle.net/11427/29789 eng application/pdf Department of Statistical Sciences Faculty of Science University of Cape Town |
| spellingShingle | Statistical Science data mining financial predictive models Hlongwane, Rivalani Willie Selecting the best model for predicting a term deposit product take-up in banking |
| thesis_degree_str | Master's |
| title | Selecting the best model for predicting a term deposit product take-up in banking |
| title_full | Selecting the best model for predicting a term deposit product take-up in banking |
| title_fullStr | Selecting the best model for predicting a term deposit product take-up in banking |
| title_full_unstemmed | Selecting the best model for predicting a term deposit product take-up in banking |
| title_short | Selecting the best model for predicting a term deposit product take-up in banking |
| title_sort | selecting the best model for predicting a term deposit product take up in banking |
| topic | Statistical Science data mining financial predictive models |
| url | http://hdl.handle.net/11427/29789 |
| work_keys_str_mv | AT hlongwanerivalaniwillie selectingthebestmodelforpredictingatermdepositproducttakeupinbanking |