Enhancing Agricultural Commodity Price Forecasting Using Generative Models: A Deep Learning Approach

G. Avinash

The Graduate School, ICAR-Indian Agricultural Research Institute, New Delhi, India.

G. H. Harish Nayak

Department of Agricultural Statistics, College of Agriculture, UAS, Dharwad, India.

Moumita Baishya *

The Graduate School, ICAR-Indian Agricultural Research Institute, New Delhi, India.

B. Samuel Naik

The Graduate School, ICAR-Indian Agricultural Research Institute, New Delhi, India.

Karthik V.C.

The Graduate School, ICAR-Indian Agricultural Research Institute, New Delhi, India.

*Author to whom correspondence should be addressed.


Abstract

Predicting stock market prices is a critical yet challenging task in finance. Technical analysis, a widely used methodology in investment theory, involves forecasting price movements by analyzing historical market data. Recently, deep learning has gained prominence for its exceptional ability to process complex data, making it a popular tool for financial applications such as stock prediction, portfolio optimization, financial information analysis, and trade execution strategies. In this study, we propose a novel deep learning architecture that integrates a Generative Adversarial Network (GAN) with a Convolutional Neural Network (CNN) as the discriminator and Gated Recurrent Units (GRU) as the generator. This framework generates distributions of daily stock prices through adversarial learning to predict stock closing prices. Using daily trading data from Ruchi Soya Industries Limited, an empirical analysis was performed across a broad time frame. Results show that the proposed GAN-based architecture significantly outperforms traditional deep learning models, including GRU, LSTM, and Bi-LSTM, in predicting stock closing prices. These findings demonstrate the potential of this novel approach for improving stock price forecasting accuracy.

Keywords: Bidirectional LSTM (Bi-LSTM), Convolutional Neural Network (CNN), discriminator, Gated Recurrent Unit (GRU), generative models, generator, Long Short-Term Memory (LSTM)


How to Cite

Avinash, G., G. H. Harish Nayak, Moumita Baishya, B. Samuel Naik, and Karthik V.C. 2024. “Enhancing Agricultural Commodity Price Forecasting Using Generative Models: A Deep Learning Approach”. Journal of Scientific Research and Reports 30 (10):1-11. https://doi.org/10.9734/jsrr/2024/v30i102424.