Page 189 - IJOCTA-15-1

An International Journal of Optimization and Control: Theories & Applications
ISSN: 2146-0957 eISSN: 2146-5703
Vol.15, No.1, pp.183-201 (2025)
https://doi.org/10.36922/ijocta.1707

RESEARCH ARTICLE

Key drivers of volatility in BIST100 firms using machine learning
segmentation

1*
Hasan H¨useyin Yildirim , Ahmet Akusta 2
1 Finance and Banking Department, Balikesir University, Turkey
2 Rectorate, Konya Technical University, Turkey
hhyildirim@balikesir.edu.tr, ahmetakusta@hotmail.com

ARTICLE INFO ABSTRACT

Article History: This study conducts a comprehensive volatility analysis among firms listed
Received: 13 October 2024 on the BIST100 index using machine learning techniques and panel regres-
Accepted: 10 December 2024 sion models. Focusing on the period from 2006 to 2023, the study excludes
Available Online: 31 January 2025 financial firms, resulting in a dataset of 46 companies. The methodology fol-
lows a two-step process: First, firms are clustered into low and high-volatility
Keywords:
groups using Principal Component Analysis (PCA) and the K-means algo-
Stock Price Volatility
rithm; second, panel regression models are applied to determine the financial
BIST100
ratios influencing stock price volatility. The Parkinson Volatility measure is
Parkinson Volatility
used as the dependent variable, while independent variables include Return
PCA
on Assets (ROA), Return on Equity (ROE), liquidity ratios, firm beta, and
Clustering Analysis
leverage ratios. Results indicate that firm beta has a statistically significant
AMS Classification 2010: positive impact on volatility across all models, while the current ratio nega-
91B84, 62P20 tively affects volatility in the model 1. These findings provide valuable insights
for investors and policymakers regarding risk management in the Turkish stock
market. Applying machine learning and advanced econometric techniques adds
to the literature on volatility forecasting and financial decision-making.

1. Introduction management strategies. Volatility can be caused
by various factors, including macroeconomic news
Financial market volatility is a critical aspect of announcements, unexpected events, and non-
economic and financial systems, influencing in- constant variance in asset prices. 1–3 These fac-
vestment decisions, risk management strategies, tors can lead to significant fluctuations in market
and the overall stability of financial markets. Un- prices, affecting the stability and performance of
derstanding the causes and implications of market different business sectors. Market volatility can
volatility is essential for investors, policymakers, be effectively analyzed and managed through the
and financial analysts. development of various statistical measures de-
signed to quantify this phenomenon.
Financial market volatility refers to the degree
of variation in the prices of financial instruments
over time. It is a key indicator of risk and un- Market volatility profoundly impacts investment
certainty in financial markets, and its accurate decisions, as it affects stock returns directly
measurement is crucial for making informed in- and indirectly through its influence on liquidity
4
vestment decisions and developing effective risk provision. High levels of volatility are typically
*Corresponding Author
183