Company Ranking Prediction Based on Network Big Data
Qihong He, Xujun Li, Yan Lindsay Sun · IETE Journal of Research · 2021
With the advent of the era of big data, it has become one of the important tasks of data mining to utilize the massive info on the internet to realize the forecast of relevant aspects. In recent years, some scholars have studied how to use company’s information for the revenue or stock forecasts, but there is very little research on inter-company ranking predictions. So from the perspective, this paper brings in the Learning-to-Rank (LtR) method into the corporation ranking prognostication, and proposes the Company Ranking Prediction Model (CRPM) grounded on LtR. First, obtain the information on the Fortune 500 official website and other correlative sites. Through data analysis, data cleaning, ranking processing, label division and data formatting, a brand-new corporation data-set containing four major categories of features (10 characteristics in total) is constructed. Then bring in four commonly utilized LtR approaches, employing the previously created data-set to train different models. Finally, each model is evaluated by the two information retrieval metrics, normalized discounted cumulative gain and mean average precision. The experimental results show that the assessment best-performing model CRPM-LambdaMART and CRPM-RandomForests can tellingly forecast the ranking of Fortune 500 companies in the next year, which has certain practical value for financiers to reasonably planning their investments and corporation managements to legitimately programming their strategic deployments.