Tools
Tools
Golecha, Yogesh Sanjay (2017) Analyzing Term Deposits in Banking Sector by Performing Predictive Analysis Using Multiple Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Abstract
This paper proposes to develop a predictive model to analyse the behavior of the customer in the banks, whether they will be applying for long-term deposit in the banks or not. The dataset is from UCI machine learning repository for the Portuguese Banking Institution for the direct marketing Campaigns. The predictive model has been developed using various machine learning techniques like Adaptive Boosting, Support Vector Machines, Logistic Regression and Decision Trees. The aim for the research is to develop a predictive model that can help the banks in acquiring more knowledge of the customers behavior for making long-term deposits in the bank and to get detailed idea about what factors contribute in achieving higher predictions. This analysis can help banks in maintaining their customers and to avoid financial risks in the banks. The model developed uses only some basic attributes of the customers that can be easily accessed and gathered by the banks. The predictive model is trained and tested for each machine learning algorithm and finally compared based on accuracy obtained by each model. From the accuracy obtained for all the four algorithms, it has been observed that Adaptive Boosting (Adaboost) has the highest accuracy and high ability to predict the behavior of the customer for applying long-term deposit in banks.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HG Finance > Banking |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Caoimhe Ní Mhaicín |
| Date Deposited: | 28 Aug 2018 16:03 |
| Last Modified: | 28 Aug 2018 16:03 |
| URI: | https://norma.ncirl.ie/id/eprint/3100 |
Actions (login required)
 |
View Item |