Paper published: "A Hybrid Method based on Machine Learning to Predict the Stock Prices in Bangladesh"

Published at IEEE IEMCON 2022, presenting a hybrid ML approach for stock price prediction in the Dhaka Stock Exchange.

Our first paper was published at the 2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON). It predicts next-day closing prices on the Dhaka Stock Exchange with a hybrid model.

A stacked LSTM forecasts the price, a GARCH(9,13) model forecasts volatility, and a linear regression combines both with moving averages and daily returns. The model is trained on over a million rows of DSE data from 2007 to 2020. I co-authored it with Md. Nabil Rahman Khan, S.M. Raiyan Reza, Most. Sadia Salsabil, Khan Md. Hasib and Mohammad Shafiul Alam.

Highlights

• Lowest RMSE on 10 of the 11 stocks tested
• Mean RMSE of 0.49, against 0.95 for linear regression and 4.34 for a stacked LSTM
• DOI: 10.1109/IEMCON56893.2022.9946610

• Research
• Publication
• Machine Learning