G12 - Asset Pricing; Trading Volume; Bond Interest RatesReturn

Traditionally, market comparison requires identifying a peer group, which still poses unresolved practical difficulties today. This research seeks to provide valuable insights into the practicality, efficiency, and accuracy of machine learning in valuing a company. It employs a state-of-the-art machine learning technique, Gradient Boosting Decision Trees (GBDT), to predict the valuation multiple directly. A yearly dataset of U.S. public companies from 1980–2021 was used. The most common multiples (EV/EBITDA, EV/EBIT, P/E, and EV/Sales) were tested. The performance of GBDT was assessed against an industry-based method. GBDT consistently outperformed the alternative method with an average 24 percentage point decrease in the median average percentage error. The results support GBDT’s potential as a supplementary tool in valuation practice.

The paper focuses on valuation multipliers for privately held companies, with the aim of developing and applying a methodological procedure to improve the accuracy of estimating the market value. This improvement is achieved through the differentiation of an industry multiplier using financial decomposition. We applied the proposed methodology enhancements to a dataset comprising 50 Czech breweries, estimating their market value using the discounted cash flow method. Importantly, our proposed modification to the methodology is not limited to this sample of breweries; its nature makes it a generally applicable procedure. Our results demonstrate that the application of our proposed procedure significantly enhances the accuracy of market value estimation for privately held companies, yielding an increase of 40–50% compared to the use of the median value.

In this paper, we empirically investigate the effect of short selling on market volatility during exogenously-induced uncertainties. Using the Covid-19 pandemic and the onset of the Russian-Ukraine Conflicts periods as event study, we employ the asymmetric EGARCH model. We show high persistence and asymmetric effects of market volatility during the pre-covid outbreak and post-covid outbreak periods. We find evidence that short selling increases market volatility during the pre-covid outbreak period while the period of the Russian-Ukraine conflict is characterized by reduced volatility. We find no evidence of short selling effect on market volatility during the post-covid outbreak period. Our findings provide significant implications for short-selling strategies during crisis periods.

This paper identifies the relationship between changes in oil prices and the returns of the world's highest-producing oil companies. Oil companies are divided into state-owned (national) and private companies. This paper focused on three different time periods to identify the relationship between changes in oil price and stock market returns by examining the specific backgrounds of each period. The results revealed that during oil's bearish market, it was more beneficial for investors to prefer state-owned companies to optimise their portfolios. The risk analysis focused on systematic risk, and the beta coefficients confirmed that state-owned companies are less sensitive to market shocks. State-owned companies are supported by governments during periods of downtrends in oil prices; therefore, they are less likely to go bankrupt. However, these companies do not have as much flexibility as private companies to cut their costs; therefore, they are more negatively affected by market movements not defined by shocks.

The paper investigates the relationship between short selling activities of stocks on the volatility of the US market and its sectors. We apply the multivariate DCC GARCH Model on the NYSE US 100 Index between November 2017 and October 2018. We find evidence that investments in some specific firms on the market reduce the market volatility and higher short selling activities reduce risk in the market. The study also finds that firms in the financial sector dominate the market and short selling activities in this sector has a greater impact on the market volatility. We also find portfolio managers to be better off investing in the market than creating portfolio within sectors.

The paper deals with the impact of the economic agent sentiment on the return for Apple and Microsoft stocks. We employed text mining procedures to analyze Twitter messages with either negative or positive sentiment towards the chosen stock titles. Those sentiments were identified by developed algorithms which are capable of identifying sentiment towards companies and also counting the numbers of tweets in the same group. This resulted in counts of tweets with positive and negative sentiment. Then we ran analysis in order to find causality between sentiment levels and the stock price of companies. To identify causal effects we applied Granger causality tests. We found bilateral causality between the risk premium and the amount of news distributed by Twitter messages.