EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
3991. A Novel Approach to Thematic Portfolio Construction: Patent-based Investment Decision Making
Invited abstract in session TC-57: Market dynamics and implications for portfolio decisions, stream Modern Decision Making in Finance and Insurance.
Tuesday, 12:30-14:00Room: S06 (building: 101)
Authors (first author is the speaker)
1. | David Jaggi
|
Banking and Finance, Zurich University of Applied Sciences | |
2. | Alexander Posth
|
Department of Banking, Finance, Insurance, ZHAW School of Management and Law | |
3. | Carsten C. Guderian
|
Chair of Technology Management, Friedrich-Alexander-University Erlangen-Nuremberg |
Abstract
In thematic investing, investors rely on long-term trends to detect and subsequently invest in what they assess as innovative companies with promising technologies. The established method for investors is to identify such companies via qualitative assessments or business sector classifications. Due to the established links between innovations, (new) technologies and patents, patent analytics has recently become an information source in thematic investing. However, there seems to be a mismatch between business sector- and technology-based classifications, which potentially affects (1) assessments in which technologies companies are active in and (2) the grouping of companies with supposedly similar technology profiles. With our research, we address these issues by analyzing the patent portfolios of the companies attributed to two Global Standard Classification Standard sectors. We examine the patent attribution profile vector of the companies in these sectors and compare them via the cosine distance metric and use clustering to group companies of high technological similarity and compare these to the S&P sectors. Further, we employ artificial intelligence tools to identify names for these newly generated clusters to ease comparability and interpret the results with a Sankey diagram analysis and a network graph analysis. Our findings yield implications for various decision-makers involved in thematic investment, including investors, corporate management, and policymakers.
Keywords
- Machine Learning
- Analytics and Data Science
- Finance and Banking
Status: accepted
Back to the list of papers