Deterministic, Stochastic, and Deep Learning Approaches to Understand the Economic Fluctuations in India

Source abstract

ABSTRACT In the present work, a new mathematical framework is proposed for studying the interrelation among population growth rate, GDP, inflation rate, and unemployment rate within deterministic and stochastic frameworks. The values of the parameters of the proposed model are estimated using real data from India. The local and global uniqueness of solutions is established for the stochastic model. The deterministic model is solved by using the Adams‐Bashforth‐Moulton predictor‐corrector method, and Milstein's method is used for solving the stochastic model. Numerical simulations correlated quite strongly with observed data, while projections for the 2024–2030 period indicate that controlled population growth bodes well for the outlook of the economy for India, supporting economic prosperity alongside reduced inflation and better employment conditions. The findings presented in this work are correlational; therefore, to find the possible cause for this phenomenon, further research is required with detailed datasets. Comparing our model's GDP predictions with that obtained using a long short‐term memory recurrent neural network model returned very high values of predictive accuracy, thus reinforcing the strength and reliability of our framework.