Logistic regression vs. artificial neural network model in prediction of financial inclusion: empirical evidence from PMJDY program in India
Rakesh Kumar et al.
What the paper says
Pradhan Mantri Jandhan Yojana (PMJDY) is a financial inclusion program launched by the Government of India in 2014 to deliver various banking services through a basic bank account feature to the vulnerable population. The primary objective of this study is to find if there is a significant difference between the two predictive models - Logistic Regression (LR) and Artificial Neural Network (ANN) in terms of classification accuracy on forecasting the account usage among the two groups of customers i.e. regular users and non-regular users. The study also uncovers the significant predictors that are important in forecasting the account usage. The results suggest both the LR and ANN models have shown good prediction accuracy. However, the findings indicate the Multilayer Perceptron Neural Network (MLPNN) using the standardised rescaling approach of a covariate has a slight better prediction than the LR model with a correct classification rate of 82.8% in the testing and validating stage of the sample cases. The practical implications of the study will provide meaningful results to the banking authorities, bureaucrats and policymakers for enriching the financial services to the underprivileged segment of the population.
3 citations
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.25 × 0.4 = 0.10 |
| M · momentum | 0.80 × 0.15 = 0.12 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.