Investor Strategies and Volatility
Pakarinen, Oskar (2021)
2021
Tuotantotalouden DI-ohjelma - Master's Programme in Industrial Engineering and Management
Tekniikan ja luonnontieteiden tiedekunta - Faculty of Engineering and Natural Sciences
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Hyväksymispäivämäärä
2021-04-12
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:tuni-202103242660
https://urn.fi/URN:NBN:fi:tuni-202103242660
Tiivistelmä
This thesis investigates investor strategies and volatility. Investors use different strategies to trade in the stock markets, and especially individual investors are prone to behavioral biases. There have been multiple attempts to cluster different investor strategies in the literature, and it has been found that clusters of investors with similar trading strategies do exist. Market volatility has also been shown to have an effect on trading activity as well as trading strategies.
We used data of Finnish large cap stocks to determine which factors affect the heterogeneity of investor strategies. The data consisted of anonymized investor IDs, stock prices and announcements per security ID. Methodically, we used multiple linear regression to study the relation between the heterogeneity of investor strategies and other factors, such as intra-daily volatility, total volume and announcements. Security IDs and seasonality factors were also controlled. The proxy for the heterogeneity of investor strategies was evaluated by calculating the degree of heterogeneity of investor strategies for each day. The intra-daily volatility was calculated for each day by dividing each day into time buckets and evaluating standard deviation of logarithmic returns.
We found that there is a statistically significant negative correlation between the proxy for the heterogeneity of investor strategies and the intra-daily volatility. This might be because investors tend to revert to herding behavior when the stock markets turn volatile. In addition, when volatility is low, investors apply a number of different non-homogeneous strategies. The total volume was also highly positively correlated with the proxy. However, this correlation was expected considering how the proxy was built. Announcements did not have a significant effect on the proxy.
We used data of Finnish large cap stocks to determine which factors affect the heterogeneity of investor strategies. The data consisted of anonymized investor IDs, stock prices and announcements per security ID. Methodically, we used multiple linear regression to study the relation between the heterogeneity of investor strategies and other factors, such as intra-daily volatility, total volume and announcements. Security IDs and seasonality factors were also controlled. The proxy for the heterogeneity of investor strategies was evaluated by calculating the degree of heterogeneity of investor strategies for each day. The intra-daily volatility was calculated for each day by dividing each day into time buckets and evaluating standard deviation of logarithmic returns.
We found that there is a statistically significant negative correlation between the proxy for the heterogeneity of investor strategies and the intra-daily volatility. This might be because investors tend to revert to herding behavior when the stock markets turn volatile. In addition, when volatility is low, investors apply a number of different non-homogeneous strategies. The total volume was also highly positively correlated with the proxy. However, this correlation was expected considering how the proxy was built. Announcements did not have a significant effect on the proxy.