| Proj No. | A3106-251 |
| Title | Stock Price Prediction Using Hybrid Machine Learning Models |
| Summary | Today, it is easy to access stock and financial information of public companies and Artificial Intelligence (AI) and Machine Learning (ML) techniques can be applied for predicting stock market. Thus, the purpose of this project is Combine ARIMA, XGBoost, and LSTM models for more accurate stock price forecasting. In the first stage, student will be required to download stock price data from Yahoo API for multiple companies. The second stage will require to Calculate technical indicators such as: Simple Moving Average (SMA), Exponential Moving Average (EMA), Relative Strength Index (RSI), Normalize and split data into training & testing sets. In the third stage, three Different Models will be trained and implemented (Combine predictions from all three models using a weighted average and Optimize weights using Grid Search or Genetic Algorithms). In the final stage, the accuracy of each model will be measured and compared. Hybrid approach is expected to provide more accurate Short-Term Stock Predictions. |
| Supervisor | A/P Mohammed Yakoob Siyal (Loc:S2 > S2 B2A > S2 B2A 28, Ext: +65 67904464) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Computer Engineering I (Loc: S2-B4c-15) |
| Single/Group: | Single |
| Area: | Digital Media Processing and Computer Engineering |
| ISP/RI/SMP/SCP?: |