DOI: 10.11118/978-80-7509-990-7-0167

COMPARATIVE ANALYSIS OF SELECTED TIME SERIES FORECASTING APPROACHES FOR INDIAN MARKETS

Ankit Tripathi¹, Arpit Tripathi¹, Oldřich Trenz¹, Pawan Kumar Mishra¹

¹ Faculty of Business and Economics, Mendel University in Brno, Zemědělská 1, 613 00 Brno, Czech Republic

Financial market analysis and prediction have been topics of interest to traders and investors for decades. This study assesses the performance of selected time series prediction methods like deep learning algorithms (Long short-term memory model (LSTM)), traditional statistical models (Seasonal Auto Regressive Integrated Moving Approach with eXogenous regressors (SARIMAX)), and advanced ensemble learning algorithms (XGBoost and FB-Prophet) using real-world data from the Indian financial market. The stock prices of Reliance Company serve as a case study, enabling a thorough evaluation of predictive accuracy and errors of the models. A pre-processing approach has been proposed and implemented, integrating significant economic factors (Gold Price, USD to INR conversion, Consumer Price Index (CPI), Wholesale Price Index (WPI) and Indian 10-year yield bond) and evaluated with technical metrics (Mean squared error, Mean Absolute Error and R2 Score). The study investigates how the inclusion of these factors impacts prediction accuracy across the selected time series prediction methods. The comparative evaluation of models before and after the pre-processing method sheds light on the evolving predictive accuracy of LSTM, SARIMAX, FB-Prophet, and XGBoost. The study showed that the SARIMAX (extension of ARIMA with seasonality and exogenous factors) and XGBOOST performed relatively well with the proposed approach while LSTM and FB prophet (though advanced) did not perform as expected in Indian financial markets. This research contributes to advancing the understanding of time series forecasting in the financial market of India, offering practical insights for decision-makers and researchers.

Keywords: Financial Time Series, Stock Market Prediction, Deep Learning in Finance, Ensemble Learning in Economics, ARIMA and XGBoost Analysis

pages: 167-186, online: 2024