Using Data Mining Methods for Investment Opportunities Identification
Abstract
Investors range from angel investors interested in early-stage start-ups to large companies that wish to expand their expertise by acquiring established businesses but a single challenge faces them all- how to identify the technological innovators and market disruptors among the millions of companies worldwide. In this paper, we explore an approach that takes an example company and sifts through the sea of options to identify a manageable number of investment alternatives. The proposed approach for company investment recommendations is non-personalized and is based on data mining and machine learning techniques. We use indirect association rules to generate investment alternatives and to identify companies that belong to similar investment portfolios. We identify several investment behavior models using density-based clustering. For matching companies to different investment types is used classification, based on the JRip algorithm. The inductive logic programming method CN2 is used for learning patterns of investment strategies. The CN2 method is used also in the core of the investment recommendation system, which for a given company generates top-N investment opportunities. Several experiments were performed with a big company knowledge graph in RDF-format with data about 7.5 million companies. The evaluation results show high accuracy of the proposed method and show a promising practical application in the financial sector, allowing companies to diversify their investment portfolio.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
By submitting a paper for publishing the authors hereby comply with the following provisions: 1. The authors retain the copyrights and only give the journal the right for first publication while licensing the work under Creative Commons Attribution License, which grants permissions to others to share the contribution citing this journal as first publication of the text. 2. The authors may enter separate, additional contractual relations for non-exclusive distribution of the published version of the work in this journal (e.g. to upload it in an institutional depository, or to be published in a book), given that they cite the first publication in this journal. 3. The authors are allowed and are encouraged to publish their works online (e.g. to upload it in an institutional depository, personal websites, social networks, etc.) before, during, and after the submission of the paper here, because this may lead to productive exchange, as well as earlier and larger referencing of the published works (see The Effect of Open Access).