Nooshin Yousefi

Jillian M. Clements, Di Xu, Nooshin Yousefi et al.

Machine learning plays an essential role in preventing financial losses in the banking industry. Perhaps the most pertinent prediction task that can result in billions of dollars in losses each year is the assessment of credit risk (i.e., the risk of default on debt). Today, much of the gains from machine learning to predict credit risk are driven by gradient boosted decision tree models. However, these gains begin to plateau without the addition of expensive new data sources or highly engineered features. In this paper, we present our attempts to create a novel approach to assessing credit risk using deep learning that does not rely on new model inputs. We propose a new credit card transaction sampling technique to use with deep recurrent and causal convolution-based neural networks that exploits long historical sequences of financial data without costly resource requirements. We show that our sequential deep learning approach using a temporal convolutional network outperformed the benchmark non-sequential tree-based model, achieving significant financial savings and earlier detection of credit risk. We also demonstrate the potential for our approach to be used in a production environment, where our sampling technique allows for sequences to be stored efficiently in memory and used for fast online learning and inference.

S. Tsianikas, N. Yousefi, J. Zhou et al.

In the wake of the highly electrified future ahead of us, the role of energy storage is crucial wherever distributed generation is abundant, such as in microgrid settings. Given the variety of storage options that are becoming more and more economical, determining which type of storage technology to invest in, along with the appropriate timing and capacity becomes a critical research question. It is inevitable that these problems will continue to become increasingly relevant in the future and require strategic planning and holistic and modern frameworks in order to be solved. Reinforcement Learning algorithms have already proven to be successful in problems where sequential decision-making is inherent. In the operations planning area, these algorithms are already used but mostly in short-term problems with well-defined constraints. On the contrary, we expand and tailor these techniques to long-term planning by utilizing model-free algorithms combined with simulation-based models. A model and expansion plan have been developed to optimally determine microgrid designs as they evolve to dynamically react to changing conditions and to exploit energy storage capabilities. We show that it is possible to derive better engineering solutions that would point to the types of energy storage units which could be at the core of future microgrid applications. Another key finding is that the optimal storage capacity threshold for a system depends heavily on the price movements of the available storage units. By utilizing the proposed approaches, it is possible to model inherent problem uncertainties and optimize the whole streamline of sequential investment decision-making.