Personalized Investment Recommendations Using Recommendation Systems
(2023) NEKN02 20231Department of Economics
- Abstract
- This paper presents a Deep Learning-based Hybrid Recommendation System (DLHR) designed specifically for institutional investors with public portfolio holdings on the Stockholm Stock Exchange. The objective is to provide personalized investment recommendations, complement existing portfolios, and explore untapped cross-selling opportunities. We evaluate the DLHR's effectiveness using selected metrics and compare it to widely used baseline methods. We utilize the mean-variance spanning tests to assess the potential for expanding the investment opportunity set. We find that investors seeking to maximize the Sharpe Ratio would have benefitted from adding the recommended stocks. Our results demonstrate that leveraging deep learning techniques... (More)
- This paper presents a Deep Learning-based Hybrid Recommendation System (DLHR) designed specifically for institutional investors with public portfolio holdings on the Stockholm Stock Exchange. The objective is to provide personalized investment recommendations, complement existing portfolios, and explore untapped cross-selling opportunities. We evaluate the DLHR's effectiveness using selected metrics and compare it to widely used baseline methods. We utilize the mean-variance spanning tests to assess the potential for expanding the investment opportunity set. We find that investors seeking to maximize the Sharpe Ratio would have benefitted from adding the recommended stocks. Our results demonstrate that leveraging deep learning techniques enables effective identification and exploitation of untapped cross-selling opportunities, leading to enhanced portfolio performance and improved risk management. Thus, we conclude that implementing the DLHR approach on the Swedish stock market can provide personalized investment recommendations for institutional investors. This research highlights the practicality of employing machine learning techniques within the financial sector. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9119216
- author
- Sadriu, Lorik LU
- supervisor
- organization
- course
- NEKN02 20231
- year
- 2023
- type
- H1 - Master's Degree (One Year)
- subject
- keywords
- Recommendation systems, Deep learning, Institutional investors, Investment decision-making, Mean-variance spanning test, Cross-Selling
- language
- English
- id
- 9119216
- date added to LUP
- 2023-11-24 08:57:34
- date last changed
- 2023-11-24 08:57:34
@misc{9119216, abstract = {{This paper presents a Deep Learning-based Hybrid Recommendation System (DLHR) designed specifically for institutional investors with public portfolio holdings on the Stockholm Stock Exchange. The objective is to provide personalized investment recommendations, complement existing portfolios, and explore untapped cross-selling opportunities. We evaluate the DLHR's effectiveness using selected metrics and compare it to widely used baseline methods. We utilize the mean-variance spanning tests to assess the potential for expanding the investment opportunity set. We find that investors seeking to maximize the Sharpe Ratio would have benefitted from adding the recommended stocks. Our results demonstrate that leveraging deep learning techniques enables effective identification and exploitation of untapped cross-selling opportunities, leading to enhanced portfolio performance and improved risk management. Thus, we conclude that implementing the DLHR approach on the Swedish stock market can provide personalized investment recommendations for institutional investors. This research highlights the practicality of employing machine learning techniques within the financial sector.}}, author = {{Sadriu, Lorik}}, language = {{eng}}, note = {{Student Paper}}, title = {{Personalized Investment Recommendations Using Recommendation Systems}}, year = {{2023}}, }