Tools
Tools
Gopalkrishna, Dheeraj (2025) A Meta-MACD Approach: Evaluating ARIMA-LSTM Generated MACD Signals for Optimizing Trade Entries in the S&P 500 Index. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (2MB) | Preview |
Abstract
The study will suggest a hybrid model as a combination of Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) networks that is not a literature review previously to produce Moving Average Convergence Divergence (MACD) signals that are best in optimizing trade entries in the S&P 500 Index. The traditional MACD indicators use historical price data, which also has lags. This study aims at reducing this limitation through proper application of linear analysis using ARIMA model and non-linear analysis using LSTM model. Based on the previous studies, the hybrid ARIMA-LSTM model will be used to predict future prices, where the signals of the meta-MACD will be obtained. Transformer model will identify support and resistance levels to select the best entry points to trade, the meta-MACD signals will be used.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Sahni, Anu UNSPECIFIED |
| Uncontrolled Keywords: | Technical Indicator Analysis; ARIMA-LSTM; MACD; S&P 500; Time Series Forecasting; Deep Learning; Trade Entry Levels |
| Subjects: | H Social Sciences > HG Finance Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence |
| Divisions: | School of Computing > Master of Science in Artificial Intelligence |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 02 Sep 2026 09:21 |
| Last Modified: | 02 Sep 2026 09:21 |
| URI: | https://norma.ncirl.ie/id/eprint/9756 |
Actions (login required)
 |
View Item |