A Study on Quantifying ESG Alpha as an access return on portfolio using ESG Sentiment in the Banking Sector with an Automated Machine Learning Approach
(2024) DABN01 20241Department of Economics
Department of Statistics
- Abstract
- This research delves into the burgeoning field of incorporating Environmental, Social, and Governance (ESG) criteria into investment strategies, spurred by a growing interest in sustainability and the demonstrated influence of ESG-related events on stock prices.
Sanctify Financial Technologies is at the forefront of quantifying firms’ ESG performance, which plays a pivotal role in this study. Various machine learning models are applied to forecast long-term stock returns for companies in the banking, financial services, and investment sectors. These models are trained on time series data spanning from 2015 to 2019, encompassing both financial metrics (ratios) and Sanctify's ESG scores, to capture comprehensive insights.
Simultaneously,... (More) - This research delves into the burgeoning field of incorporating Environmental, Social, and Governance (ESG) criteria into investment strategies, spurred by a growing interest in sustainability and the demonstrated influence of ESG-related events on stock prices.
Sanctify Financial Technologies is at the forefront of quantifying firms’ ESG performance, which plays a pivotal role in this study. Various machine learning models are applied to forecast long-term stock returns for companies in the banking, financial services, and investment sectors. These models are trained on time series data spanning from 2015 to 2019, encompassing both financial metrics (ratios) and Sanctify's ESG scores, to capture comprehensive insights.
Simultaneously, this study aims to predict long-term returns for investments spanning over three years, leveraging machine learning models that are trained on historical data from 2015 to 2019. The models integrate both ESG scores from Sanctify Financial Technologies and financial metrics specific to the banking, financial services, and investment sectors. The predictions are then performed on 2020 financial data and corresponding ESG scores, allowing for a robust evaluation of the models' predictive accuracy and the impact of ESG factors on long-term investment performance.
The significance of the ESG variable in the model is rigorously assessed using various statistical tests, demonstrating a high level of significance in influencing long-term investment returns. Furthermore, the proposed portfolio constructed based on a model incorporating ESG scores achieves a cumulative return higher than a portfolio built solely on financial ratios, indicating the added value of ESG considerations in investment decision-making processes. However, despite these advantages, both portfolios, with and without ESG corporation, do not outperform a benchmark S&P 500 portfolio return over the three-year period studied. This comparative analysis provides valuable insights into the relative performance of ESG-informed investment strategies within the context of broader market benchmarks.
Through this comprehensive evaluation, stakeholders can gain a nuanced understanding of the impact of ESG factors on investment performance and the potential trade-offs between sustainability considerations and market benchmark performance. These insights contribute to ongoing discussions in sustainable finance and investment strategy development. (Less) - Popular Abstract
- This research delves into the burgeoning field of incorporating Environmental, Social, and Governance (ESG) criteria into investment strategies, spurred by a growing interest in sustainability and the demonstrated influence of ESG-related events on stock prices.
Sanctify Financial Technologies is at the forefront of quantifying firms’ ESG performance, which plays a pivotal role in this study. Various machine learning models are applied to forecast long-term stock returns for companies in the banking, financial services, and investment sectors. These models are trained on time series data spanning from 2015 to 2019, encompassing both financial metrics (ratios) and Sanctify's ESG scores, to capture comprehensive insights.
Simultaneously,... (More) - This research delves into the burgeoning field of incorporating Environmental, Social, and Governance (ESG) criteria into investment strategies, spurred by a growing interest in sustainability and the demonstrated influence of ESG-related events on stock prices.
Sanctify Financial Technologies is at the forefront of quantifying firms’ ESG performance, which plays a pivotal role in this study. Various machine learning models are applied to forecast long-term stock returns for companies in the banking, financial services, and investment sectors. These models are trained on time series data spanning from 2015 to 2019, encompassing both financial metrics (ratios) and Sanctify's ESG scores, to capture comprehensive insights.
Simultaneously, this study aims to predict long-term returns for investments spanning over three years, leveraging machine learning models that are trained on historical data from 2015 to 2019. The models integrate both ESG scores from Sanctify Financial Technologies and financial metrics specific to the banking, financial services, and investment sectors. The predictions are then performed on 2020 financial data and corresponding ESG scores, allowing for a robust evaluation of the models' predictive accuracy and the impact of ESG factors on long-term investment performance.
The significance of the ESG variable in the model is rigorously assessed using various statistical tests, demonstrating a high level of significance in influencing long-term investment returns. Furthermore, the proposed portfolio constructed based on a model incorporating ESG scores achieves a cumulative return higher than a portfolio built solely on financial ratios, indicating the added value of ESG considerations in investment decision-making processes. However, despite these advantages, both portfolios, with and without ESG corporation, do not outperform a benchmark S&P 500 portfolio return over the three-year period studied. This comparative analysis provides valuable insights into the relative performance of ESG-informed investment strategies within the context of broader market benchmarks.
Through this comprehensive evaluation, stakeholders can gain a nuanced understanding of the impact of ESG factors on investment performance and the potential trade-offs between sustainability considerations and market benchmark performance. These insights contribute to ongoing discussions in sustainable finance and investment strategy development. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9154842
- author
- Babaeva, Maria LU
- supervisor
- organization
- course
- DABN01 20241
- year
- 2024
- type
- H1 - Master's Degree (One Year)
- subject
- keywords
- ESG alpha, financial data, prediction, AI in finance, machine learning, quantitative investment
- language
- English
- id
- 9154842
- date added to LUP
- 2024-09-24 08:32:12
- date last changed
- 2024-09-24 08:32:12
@misc{9154842, abstract = {{This research delves into the burgeoning field of incorporating Environmental, Social, and Governance (ESG) criteria into investment strategies, spurred by a growing interest in sustainability and the demonstrated influence of ESG-related events on stock prices. Sanctify Financial Technologies is at the forefront of quantifying firms’ ESG performance, which plays a pivotal role in this study. Various machine learning models are applied to forecast long-term stock returns for companies in the banking, financial services, and investment sectors. These models are trained on time series data spanning from 2015 to 2019, encompassing both financial metrics (ratios) and Sanctify's ESG scores, to capture comprehensive insights. Simultaneously, this study aims to predict long-term returns for investments spanning over three years, leveraging machine learning models that are trained on historical data from 2015 to 2019. The models integrate both ESG scores from Sanctify Financial Technologies and financial metrics specific to the banking, financial services, and investment sectors. The predictions are then performed on 2020 financial data and corresponding ESG scores, allowing for a robust evaluation of the models' predictive accuracy and the impact of ESG factors on long-term investment performance. The significance of the ESG variable in the model is rigorously assessed using various statistical tests, demonstrating a high level of significance in influencing long-term investment returns. Furthermore, the proposed portfolio constructed based on a model incorporating ESG scores achieves a cumulative return higher than a portfolio built solely on financial ratios, indicating the added value of ESG considerations in investment decision-making processes. However, despite these advantages, both portfolios, with and without ESG corporation, do not outperform a benchmark S&P 500 portfolio return over the three-year period studied. This comparative analysis provides valuable insights into the relative performance of ESG-informed investment strategies within the context of broader market benchmarks. Through this comprehensive evaluation, stakeholders can gain a nuanced understanding of the impact of ESG factors on investment performance and the potential trade-offs between sustainability considerations and market benchmark performance. These insights contribute to ongoing discussions in sustainable finance and investment strategy development.}}, author = {{Babaeva, Maria}}, language = {{eng}}, note = {{Student Paper}}, title = {{A Study on Quantifying ESG Alpha as an access return on portfolio using ESG Sentiment in the Banking Sector with an Automated Machine Learning Approach}}, year = {{2024}}, }