Analysis of Stock Market Predicting Future Trend using ML
Velayutham Murugan, V. R. Thejeshwar, A. Vijayaraj, K Saravanan, R. Megavannan, P. Rajeswari · 2024
Predicting future movements in stock prices is a topic of intense interest in the world of Fintech. Non-Standard Dynamics and complicated interplays of the stock market make effective stock profiling difficult. The majority of currently available methods either treat each stock individually or look for really basic with uniform patterns. In practice, there are many potential sources of stock market connection, and signs about underlying relationships are sometimes hidden in elaborate graphs. Hierarchical Adaptive Temporal-Relational Interaction model for cascading dilated convolutions and gating routes to understand the regularities of dynamic transitions in stock market. We considered stock pair matching, in particular, happens at each time stage rather than waiting for the last flattened representations, while relevant feature points and enhancement are determined taking time attenuation into account. Lastly, we optimize the stock representations using regularized global clusters representation. The efficacy of our suggested model is demonstrated experimentally based on three actual stock market datasets.