The Journal of Prediction Markets https://ubplj.org/index.php/jpm <p>The Journal of Prediction Markets is an academic peer reviewed journal publishing articles, both commissioned and submitted, survey articles, case studies and book reviews.</p> <p>Editor: Leighton Vaughan Williams</p> University of Buckingham Press en-US The Journal of Prediction Markets 1750-6751 Classification in Horse Race Prediction Through Principal Component Decomposition https://ubplj.org/index.php/jpm/article/view/2093 <p>The established view for horse race handicapping and staking strategies is to model them as a classification problem using factors describing horse, jockey, trainer, and racing history coupled with public odds, solved via a logistic regression. Logistic regression probabilities are then normalised, and bets filtered by threshold, or anomalous pricing. However, published algorithms do not show systematic profitability, nor do machine learning approaches using algorithmic betting strategies. This deficiency is due to three factors. First, wins are rare and racing data are thus imbalanced. Second, racing factors are multicollinear. Third, the number of factors needed for accurate prediction is very large. We show that alternative methods using variants from principal component analysis produces sustainable profitability regardless of staking strategy through a reduction of factors to fundamental drivers. We apply a partial least squares regression methodology to Australian thoroughbred racing. This approach is shown to outperform logistic regression and machine learning methods in classifying winners for a profitable trading strategy. This method can be applied to multiple betting domains.</p> Jason West Vlad Kazakov Copyright (c) 2024 The Journal of Prediction Markets 2024-07-01 2024-07-01 18 1 3 20 10.5750/jpm.v18i1.2093 COVID‐19 and Hospitality and Tourism Stock Indices: Insights from European Markets https://ubplj.org/index.php/jpm/article/view/2102 <p>Threatening tourism’s core values, COVID-19 forced a global lockdown with unprecedent economic ramifications across the industry’s sectors. By espousing an econometric methodology, this study investigates the pandemic’s impact on hospitality and tourism (H/T) stock indices trading in five European stock markets and explores the effect of both state-enforced, non-pharmaceutical interventions (NPIs) and vaccinations. Findings suggest that a) the pandemic was the most impactful event in history to affect H/T stock indices trading in major European financial markets; b) the tourism industry reacted differently to the pandemic compared to other major economic sectors; and c) government-enforced measures directly targeting the industry’s core operations had a powerful effect on both stock returns and volatility during the first year of the pandemic, nevertheless, for returns, this effect was mitigated by the rollout of vaccinations. The study enriches our collective knowledge on the impact of COVID-19 on the economics of tourism, with emphasis on H/T stock indices.</p> Anastasios Zopiatis Christos S. Savva Neophytos Lambertides Copyright (c) 2024 The Journal of Prediction Markets 2024-07-01 2024-07-01 18 1 21 46 10.5750/jpm.v18i1.2102 Predicting the Winner of a Twenty20 International Cricket Match: Classification and Explainable Machine Learning Approach https://ubplj.org/index.php/jpm/article/view/2109 <p>We present a supervised machine learning approach to predict the winner of a Twenty20 (T20) international match. The prediction dynamically changes as the match progresses. We also use explainable machine learning techniques (SHAP scores) to understand the importance of various features in making the decision at various stages of the T20 match. We present results on a dataset of 808 men's T20 international matches. The dynamic accuracy increases from about 55% in the initial stages of the T20 match to a maximum of about 85% in the final stages of the match (with an overall accuracy of about 63% in innings 1 and 74% in innings 2). SHAP scores reveal that team strength is an important feature in making the prediction in initial stages of the match; however, in the final stages, match situation plays the dominant role in the decision making process. Our work may help team coaches and captains to assess their chances of winning and/or chart a course towards winning in the ongoing T20 match, as well as be useful for sports analytics and gambling websites and apps.</p> Yash Agrawal Kundan Kandhway Copyright (c) 2024 The Journal of Prediction Markets 2024-07-01 2024-07-01 18 1 47 64 10.5750/jpm.v18i1.2109 Asymmetric Impact of Russia–Ukraine War on Global Stock Markets https://ubplj.org/index.php/jpm/article/view/2115 <p>Russia’s invasion of Ukraine on February 24, 2022, emerged as Europe’s most significant military conflict post second world war, with global economic and geopolitical consequences. Using a broad (95-country) sample, the study examines the impact of the Russia–Ukraine war on global stock markets surrounding the war announcement. It applied the event study method and used short and long event windows to examine the war’s immediate and intermediate impacts. Global stock markets delivered negative 1.90% abnormal returns on the day of the war announcement, and Russia saw the biggest fall. However, after the initial adverse reaction, stock markets reacted asymmetrically. Stock markets of the countries in geographic proximity and high trade intensity with Russia and Ukraine, and net importers of energy and food grains negatively reacted more than the rest. The regional results show that Asia Pacific and Europe reported negative returns across event windows. In contrast, the Americas, Africa, and the Middle East did not react negatively, even in the shortest event window. Adverse war reactions moderated over time. Equity investors and portfolio managers who aim to protect their investments should buy stocks in countries that are net exporters of commodities made in war-torn countries and switch to stock markets geographically far from the war zone.</p> Mayank Joshipura Ashu Lamba Copyright (c) 2024 The Journal of Prediction Markets 2024-07-01 2024-07-01 18 1 65 84 10.5750/jpm.v18i1.2115 Forecasting Road Accident Deaths in India Using SARIMA https://ubplj.org/index.php/jpm/article/view/2116 <p>Road accidents are one of the leading causes of death worldwide. The present study analysed the pattern of road accident deaths in India from the year 2014 till the year 2022. The data was taken from the government website, and we have split it into training and testing datasets. The training dataset was from the year 2014 to 2020, and the forecasting was done for the years 2021 and 2022. We have used the SARIMA model to forecast the number of road accidents in India for the years 2021 and 2022. The accuracy of the SARIMA model in forecasting the number of road accidents in India is also established in the present study. The study has insights for policymakers and administrators. Some of the policies that can be enforced to decrease the number of road accidents in India are better road infrastructure for vehicles across India, enforcement of safety regulations, easy access to trauma care centres, strictly following the speed limits on the road and so on.</p> Saurabh Kumar Copyright (c) 2024 The Journal of Prediction Markets 2024-07-01 2024-07-01 18 1 85 96 10.5750/jpm.v18i1.2116 Parimutuel versus Fixed-Odds Betting: Evidence from a Hybrid Market https://ubplj.org/index.php/jpm/article/view/2118 <pre>Betting markets on horse races have typically taken one of two forms: 1) a parimutuel pool, where prices are uncertain until the market is closed, or 2) a fixed-odds market, where prices are fixed at the time the bet is placed. I study a hybrid betting mar- ket where a pool is run side-by-side with a fixed-odds market, and the two are then combined to determine final pool prices. I find that the fixed-odds market is quicker to aggregate information, and produces comparatively efficient prices from the start of betting. Interim prices in the parimutuel pool are largely uninformative, but improve as betting progresses. The parimutuel pool in this hybrid market also serves two ad- ditional purposes. It allows bettors to avoid thin early trading, and also provides a mechanism for extracting information in late leftover quotes in the fixed-odds market.</pre> Alasdair Brown Copyright (c) 2024 The Journal of Prediction Markets 2024-07-01 2024-07-01 18 1 97 114 10.5750/jpm.v18i1.2118 Forecasting ASEAN-5 Stock Index Price Movement Using Machine Learning Techniques https://ubplj.org/index.php/jpm/article/view/2119 <p>This research investigates the effectiveness of various machine learning models, including Random Forest, Neural Networks, Adaboost, Discriminant Analysis, Logit Model, Support Vectors, and Kernel Factory. The study aims to forecast fluctuations in the ASEAN-5 stock index prices within an eleven-year period. The study provides useful information about how well machine learning techniques can predict changes in the stock market, with potential implications for both academic researchers and market participants. The findings imply that Adaboost consistently outperforms all others in predicting price changes accurately. This shows that machine learning algorithms are capable of accurately forecasting the movement of the ASEAN-5 stock index values. This study contributes to the growing body of research on the use of machine learning techniques in finance and provides investors with information to make informed decisions about investments in the ASEAN-5 region, ultimately leading to increased returns and improved portfolio performance.</p> Muneer Shaik Abhishek Sahjwani Kesava Sai Krishna Kondepudi Copyright (c) 2024 The Journal of Prediction Markets 2024-07-01 2024-07-01 18 1 115 140 10.5750/jpm.v18i1.2119