A STOCHASTIC PROCESS-BASED RISK MODEL WHICH INVOLVES A PUT OPTIONS TO VALUE-AT-GAIN FORECAST

• Main Author: Diyanni Mulya, Nurma
• Format: Theses
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/76464
• Institution: Institut Teknologi Bandung

Risk can be defined as a loss that occurs in investment. Risk is an uncertainty, so risk is often modeled statistically so that it can be quantified and analyzed objectively. Quantification of risk can be done through a random variable. In a wider context, risk can also include potential gains or positive consequences. In this thesis, risk modeling is performed from the gain perspective by involving the stochastic dynamics of an asset price. In simplified or classical risk modeling, options are often ignored or oversimplified, when in fact options are an important feature of risk management as it provides flexibility and significant risk reduction potential. Therefore, a stochastic process-based risk model that includes options is the main model used in this thesis. In addition, constant model parameters are modified into stochastic parameters through AR and ARMA conditional mean models, as well as ARCH and GARCH volatility models. The magnitude of risk is quantified using the Value-at-Gain (VaG) risk measure. VaG is a risk measure that uses the concept of Value-at-Risk (VaR) risk measure. VaG represents the maximum potential gain at a given confidence level. The results of VaG are used to analyze the effectiveness of options in risk management, which helps reduce or mitigate the risks that may occur. In other words, involving options in risk models can provide a more comprehensive understanding of the risks faced and take effective steps to reduce these risks. It is hoped that the results of this study can provide better insights into risk management strategies and assist financial professionals to make smarter decisions in managing risks.