| Autor: |
Manish Joshi, Yogita S. Patil |
| Rok vydání: |
2020 |
| Předmět: |
|
| Zdroj: |
2020 International Conference on System, Computation, Automation and Networking (ICSCAN). |
| DOI: |
10.1109/icscan49426.2020.9262356 |
| Popis: |
Trend prediction of the volatile stock market has been an interesting and challenging task for many researchers over many years. In this paper, we present how rough set-based BIRCH clustering can be used to develop stock data prediction model. The proposed model augments clustering with a popular technical analysis method called candlestick. BIRCH clustering algorithm is used to group stocks of varied sectors by taking into consideration the previous few days volatility. Further cluster analysis is carried out to predict stocks movement for next trading day. The proposed prediction model is different from existing models as it works on all NSE stocks from varied sector. Our model outperforms models that merely using clustering or candlestick techniques. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
