Centrality measures on segmented entropy networks to identify influencers and influencees for financial market scenario

The rise and fall in stock prices are responsible for creating an influence over intra- and inter-sectoral stocks. Through usual market transactions, the mutual dependencies among the stocks/companies are evolved. These kinds of influential effects can be adequately captured by the amount of directional information flow. In this context, attempts have been made to exhibit these kinds of directional influences through segmented entropy networks (e.g., strong, moderate, and weak) using transfer entropy measures. Moreover, these segmentations are required to differentiate different levels of information flow and reduce information loss which might occur for using threshold values during network construction. Naturally, the mutual dependencies among the stocks rely on the dynamic relationships among the influencers and influencees. The existing centralities cannot effectively capture the two aspects of influential nodes. To address the problem, attempts have been made to identify the influencees and influencers in any network through the proposed in-centrality and out-centrality measures. Their performance is compared using the NSE (National Stock Exchange) dataset of India with other existing centralities. It is noted that the financial and energy sectors drive the market as a whole during the period of study. On the other hand, the health care, basic material, and consumer defensive sectors create a moderate impact on the market. Additionally, the influential stocks have high market capitalization and generated high market revenue at that time. The effectiveness of the proposed model has also been compared in terms of its spreading efficacy using a weighted independent cascade model. In addition, the performance results have been validated through the Mann–Whitney U-test. The p-values among the pair of distributions of spreading performance are significantly less than 0.05 for both weak and strong entropy networks which reveal the effectiveness of the models.