Forecasting the Dynamics of Income and Wealth Inequality in India Using ARIMA-LSTM Hybrid Nonlinear Machine Learning Models

D P Singh; Khelendra Kumar Yadav

doi:10.36948/ijfmr.2026.v08i04.84907

Forecasting the Dynamics of Income and Wealth Inequality in India Using ARIMA-LSTM Hybrid Nonlinear Machine Learning Models

Author(s)	Dr. D P Singh, Mr. Khelendra Kumar Yadav
Country	India
Abstract	Income and wealth inequality have emerged as significant socio-economic concerns in India, even amid sustained economic expansion. Traditional econometric approaches often struggle to adequately capture the intricate linear and nonlinear patterns that characterize inequality dynamics over time. To address this limitation, the present study introduces a hybrid ARIMA–LSTM forecasting framework that combines the linear forecasting capability of the Autoregressive Integrated Moving Average (ARIMA) model with the nonlinear learning capacity of Long Short-Term Memory (LSTM) neural networks, thereby enhancing the accuracy of income and wealth inequality predictions. Annual time-series data spanning the period 1990–2024 were compiled from multiple authoritative sources, including the World Inequality Database (WID), the World Bank, the Reserve Bank of India (RBI), the National Sample Survey (NSS), the Periodic Labour Force Survey (PLFS), and the Ministry of Statistics and Programme Implementation (MoSPI). The analytical framework incorporates a comprehensive set of socio-economic indicators, including the Gini coefficient, income shares of the top 1%, top 10%, and bottom 50% of the population, wealth concentration, per capita income, unemployment rate, inflation, educational attainment, and public social expenditure. Model performance is evaluated using MAE, RMSE, MAPE, and R², with comparisons against standalone ARIMA and LSTM models. Results demonstrate that the ARIMA–LSTM hybrid model achieves superior forecasting accuracy by effectively capturing both linear and nonlinear temporal patterns. Forecasts to 2045 indicate a continued rise in income and wealth concentration, highlighting persistent inequality under current economic conditions. The proposed framework contributes to computational economics by providing a robust tool for long-term socio-economic forecasting and offers evidence-based insights for policies promoting inclusive growth, equitable wealth distribution, poverty reduction, and sustainable economic development in India.
Keywords	Income Inequality; Wealth Inequality; India; ARIMA–LSTM Hybrid; Machine Learning; Time-Series Forecasting; Deep Learning; ARIMA; LSTM; Economic Inequality; Wealth Concentration; Nonlinear Forecasting; Computational Economics; Sustainable Development; Inclusive Growth.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 4, July-August 2026
Published On	2026-08-01
DOI	https://doi.org/10.36948/ijfmr.2026.v08i04.84907

View / Download PDF File

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Forecasting the Dynamics of Income and Wealth Inequality in India Using ARIMA-LSTM Hybrid Nonlinear Machine Learning Models

Share this