Charles Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Charles Lee has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Gilbert Fridgen
University of Luxembourg
2 shared publications - Joaquin Delgado Fernandez
Interdisciplinary Centre for Security, Reliability and Trust (SnT), https://ror.org/036x5ad56 University of Luxembourg , Esch-sur-Alzette, Luxembourg
2 shared publications - Sergio Potenciano Menci
Interdisciplinary Centre for Security, Reliability and Trust (SnT), https://ror.org/036x5ad56 University of Luxembourg , Esch-sur-Alzette, Luxembourg
2 shared publications - Alexander Rieger
University of Arkansas
1 shared publication
Latest Publications
- Open Access
- 1 January 2023
- Published by HICSS Conference Office
Federated Learning for Credit Risk Assessment
Credit risk assessment is a standard procedure for financial institutions (FIs) when estimating their credit risk exposure. It involves the gathering and processing quantitative and qualitative datasets to estimate whether an individual or entity will be able to make future required payments. To ensure effective processing of this data, FIs increasingly use machine learning methods. Large FIs often have more powerful models as they can access larger datasets. In this paper, we present a Federated Learning prototype that allows smaller FIs to compete by training in a cooperative fashion a machine learning model which combines key data derived from several smaller datasets. We test our prototype on an historical mortgage dataset and empirically demonstrate the benefits of Federated Learning for smaller FIs. We conclude that smaller FIs can expect a significant performance increase in their credit risk assessment models by using collaborative machine learning.
- 1 January 2023
- Published by HICSS Conference Office
Open AccessFederated Learning for Credit Risk Assessment
Credit risk assessment is a standard procedure for financial institutions (FIs) when estimating their credit risk exposure. It involves the gathering and processing quantitative and qualitative datasets to estimate whether an individual or entity will be able to make future required payments. To ensure effective processing of this data, FIs increasingly use machine learning methods. Large FIs often have more powerful models as they can access larger datasets. In this paper, we present a Federated Learning prototype that allows smaller FIs to compete by training in a cooperative fashion a machine learning model which combines key data derived from several smaller datasets. We test our prototype on an historical mortgage dataset and empirically demonstrate the benefits of Federated Learning for smaller FIs. We conclude that smaller FIs can expect a significant performance increase in their credit risk assessment models by using collaborative machine learning.
- Open Access
Privacy-preserving Federated Learning for Residential Short Term Load Forecasting
With high levels of intermittent power generation and dynamic demand patterns, accurate forecasts for residential loads have become essential. Smart meters can play an important role when making these forecasts as they provide detailed load data. However, using smart meter data for load forecasting is challenging due to data privacy requirements. This paper investigates how these requirements can be addressed through a combination of federated learning and privacy preserving techniques such as differential privacy and secure aggregation. For our analysis, we employ a large set of residential load data and simulate how different federated learning models and privacy preserving techniques affect performance and privacy. Our simulations reveal that combining federated learning and privacy preserving techniques can secure both high forecasting accuracy and near-complete privacy. Specifically, we find that such combinations enable a high level of information sharing while ensuring privacy of both the processed load data and forecasting models. Moreover, we identify and discuss challenges of applying federated learning, differential privacy and secure aggregation for residential short-term load forecasting.
Open AccessPrivacy-preserving Federated Learning for Residential Short Term Load Forecasting
With high levels of intermittent power generation and dynamic demand patterns, accurate forecasts for residential loads have become essential. Smart meters can play an important role when making these forecasts as they provide detailed load data. However, using smart meter data for load forecasting is challenging due to data privacy requirements. This paper investigates how these requirements can be addressed through a combination of federated learning and privacy preserving techniques such as differential privacy and secure aggregation. For our analysis, we employ a large set of residential load data and simulate how different federated learning models and privacy preserving techniques affect performance and privacy. Our simulations reveal that combining federated learning and privacy preserving techniques can secure both high forecasting accuracy and near-complete privacy. Specifically, we find that such combinations enable a high level of information sharing while ensuring privacy of both the processed load data and forecasting models. Moreover, we identify and discuss challenges of applying federated learning, differential privacy and secure aggregation for residential short-term load forecasting.