Qianqian Sun
ABSTRACT
Under the background of the influence of financial crisis and European debt crisis on commercial banks, this paper takes Santander bank as an example to propose a model for forecasting customer transactions. The model mainly uses decision tree, logistic regression model and neural network. Through data mining, variable selection, variable dimensionality reduction and other methods, the model is constantly adjusted and optimized, and finally a relatively superior model is obtained. This model can help Santander bank to determine which customers will forecast future specific transactions, so as to help the company improve its marketing strategy and increase customer churn rate.
- Wei-Yang Lin, Ya-Han Hu, Chih-Fong Tsai. (2012) Machine Learning in Financial Crisis Prediction: A Survey. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42(4), 421--436. Google Scholar
Digital Library
- José Antonio Sanz, Dario Bernardo, Francisco Herrera, et al. (2015) A Compact Evolutionary Interval-Valued Fuzzy Rule-Based Classification System for the Modeling and Prediction of Real-World Financial Applications With Imbalanced Data. IEEE Transactions on Fuzzy Systems, 23(4), 973--990.Google ScholarDigital Library
- V. Schetinin, L. Jakaite, W. Krzanowski. (2018) Bayesian averaging over decision tree models: An application for estimating uncertainty in trauma severity scoring. International Journal of Medical Informatics, 112(4), 6--14.Google ScholarCross Ref
- Nussaïbah B. Raja, Ihsan Çiçek, Necla Türkoğlu, et al. (2018) Correction to: Landslide susceptibility mapping of the Sera River Basin using logistic regression model. Natural Hazards, 91(3), 1323--1446.Google ScholarCross Ref
- Jarosaw Brodny, Magdalena Tutak. (2020) The Use of Artificial Neural Networks to Analyze Greenhouse Gas and Air Pollutant Emissions from the Mining and Quarrying Sector in the European Union. Energies, 2020, 13(8), DOI: 10.3390/en13081925.Google Scholar
- Guoqiang Zhang, Benxiu Liu, Yingting Guo, et al. (2018) Sea State Bias Estimation with Least Absolute Shrinkage and Selection Operator (LASSO). Journal of Ocean University of China, 2018, 17(5), 1019--1025.Google Scholar
Index Terms
- Construction of Santander Bank Customer Transaction Forecast Model
Recommendations
Improving Purchase Forecast for Cosmetics by Modelling Customer Purchase Behavior
ICEME '19: Proceedings of the 2019 10th International Conference on E-business, Management and EconomicsThe traditional inventory forecasting method cannot accurately predict the demand of cosmetics consumer market, because cosmetics market has too many imported items, seasons discount, festival discount promotions, product combination promotions, and ...
Mining customer knowledge for direct selling and marketing
Research highlights Direct marketing is an effective marketing method. Direct marketing could provide exclusive products and services for specific consumers. This study analyzes consumer adumbration, lifestyle habits and purchasing behavior using data ...
A recommender system to avoid customer churn
A major concern for modern enterprises is to promote customer value, loyalty and contribution through services such as can help establish a long-term, honest relationship with customers. For purposes of better customer relationship management, data ...
Comments