Prof. Khreshna's Scientific Address: Harnessing Stochastic Predictions to Mitigate Financial and Insurance Risks
By Erika Winfellina Sibarani -
Editor Vera Citra Utami
BANDUNG, itb.ac.id — Quantitative risk is inherently stochastic, meaning it can be quantified using random variables and is probabilistic in nature. Such risks are prevalent in finance and insurance sectors, encompassing scenarios like cryptocurrency volatility, energy market fluctuations, and insurance claim payouts. The future challenges of stochastic risk involve leveraging technology to provide accurate risk predictions and utilizing these predictions to achieve efficient financial security.
These challenges were the focal point of Prof. Khreshna Imaduddin Ahmad Syuhada's scientific address titled “From Random Risks to Risk Measures: Stochastic Predictions for Financial and Insurance Risks.”
This address was delivered during the Institut Teknologi Bandung Professorial Forum (FGB ITB) on Saturday, June 22, 2024, at the Aula Barat in ITB Ganesha Campus.
Currently, Prof. Khreshna is a member of the Senate of the Faculty of Mathematics and Natural Sciences (FMNS) at ITB. He is actively engaged in research within the field of statistics, has published numerous scholarly articles, and authored several books. His dedication to academia was recognized with several awards, including the ITB 25-Year Service Award in 2023.
Prof. Khreshna provided an in-depth explanation of quantitative risk and its management. “Quantitative risk management is conducted through two main stages. The first stage involves defining the appropriate random risk for the loss phenomenon. For example, in finance, risk can be viewed as the negative of returns. The second stage is to compute or predict the forthcoming random risk using risk measures,” he explained.
He further elaborated on the statistical aspects related to risk. “Risk phenomena must be quantifiable through a real-valued function, which is then referred to as random risk distributed statistically. We predict random risks using risk measures. The tools we use for calculating and predicting these measures are distribution functions. Two well-known risk measures are Value-at-Risk (VaR) and Expected Shortfall (ES). VaR is based on probability, while ES is based on expectation. Both risk measures have been expanded or modified in various directions,” he said.
Additionally, Prof. Khreshna discussed the development of risk models across various financial and insurance risks. In finance, he mentioned the risk of the cryptocurrency market and its relation to energy market risk. In the insurance domain, he addressed risks such as claim frequency and severity, insurance-reinsurance contract risks, and longevity (mortality) risks.
Prof. Khreshna emphasized that the behavior of stochastic risks is dynamic, evolving with human thought processes, resource availability, and technological advancements. Therefore, risk models must be continuously refined and expanded to achieve the desired accuracy and provide effective financial risk management.
