Recognising innovative companies by using a diversified stacked generalisation method for website classification

Abstract

In this paper, we propose a classification system which is able to decide whether a company is innovative or not, based only on its public website available on the internet. As innovativeness plays a crucial role in the development of myriad branches of the modern economy, an increasing number of entities are expending effort to be innovative. Thus, a new issue has appeared: how can we recognise them? Not only is grasping the idea of innovativeness challenging for humans, but also impossible for any known machine learning algorithm. Therefore, we propose a new indirect technique: a diversified stacked generalisation method, which is based on a combination of a multi-view approach and a genetic algorithm. The proposed approach achieves better performance than all other classification methods which include: (i) models trained on single datasets; or (ii) a simple voting method on these models. Furthermore, in this study, we check if unaligned feature space improves classification results. The proposed solution has been extensively evaluated on real data collected from companies' websites. The experimental results verify that the proposed method improves the classification quality of websites which might represent innovative companies.

Strategic leadership and technological innovation: A comprehensive review and research agenda

“…For example, scholars could try to capture the public's perceptions of firms' innovativeness through semantic analyses of press coverage (Graf‐Vlachy, Oliver, Banfield, König, & Bundy, 2020), sentiment analyses of social media data (Gautam & Yadav, 2014), or analyses of company rankings (e.g., Forbes, 2018). Alternative ways of determining the quantity and quality of newly developed products, services, and processes could include systematic analyses of trademark filings (Castaldi, 2020), the content and structure of company websites (Mirończuk & Protasiewicz, 2020) or mission statements (Hanisch, Haeussler, Graf‐Vlachy, König, & Cho, 2018), firms' 10‐K filings (Hoberg & Phillips, 2016), or analyst reports (Bellstam, Bhagat, & Cookson, 2020). Finally, other output‐oriented measures could target process innovations, which have rarely been considered in the extant literature (Haneda & Ito, 2018; Qian, Cao, & Takeuchi, 2013; Swink, 2000).…”

SUBiNN: a stacked uni- and bivariate kNN sparse ensemble

“…Breiman (1996) proposed a regression metalearner, and noted that using the cross-validated base-learner predictions is necessary to avoid over-fitting. The literature lacks studies of stacking solely kNN models, but using a combination of support vector machines, kNN, and random forest is common (Mirończuk and Protasiewicz 2019;Wang et al 2019;Yadrintsev and Sochenkov 2019).…”