Forecasting stock price movements for intra-day trading using transformers and LSTM
Author(s): Aman Sehgal
Abstract: For several years people have tried to find a scientific technique for time series forecasting in the world of stock market trading. A widely applicable model to forecast stock fluctuations can prove to be revolutionary in the worlds of both finance and data analysis. The advent of artificial intelligence and machine learning has sparked a new energy in the quest for algorithm designs. This quest is ignited further since the advent of neural networks and state-of-the-art transformer models. This research envisages taking this quest further ahead by developing a transformer-based model for intra-day stock forecasting. The study takes into account select Nifty 50 stocks and focuses primarily on the Indian stock market.