Investigating the efficiency of the Asian handicap football betting market with ratings and Bayesian networks

Despite the massive popularity of the Asian Handicap (AH) football (soccer) betting market, its efficiency has not been adequately studied by the relevant literature. This paper combines rating systems with Bayesian networks and presents the first published model specifically developed for prediction and assessment of the efficiency of the AH betting market. The results are based on 13 English Premier League seasons and are compared to the traditional market, where the bets are for win, lose or draw. Different betting situations have been examined including a) both average and maximum (best available) market odds, b) all possible betting decision thresholds between predicted and published odds, c) optimisations for both return-on-investment and profit, and d) simple stake adjustments to investigate how the variance of returns changes when targeting equivalent profit in both traditional and AH markets. While the AH market is found to share the inefficiencies of the traditional market, the findings reveal both interesting differences as well as similarities between the two.

Market efficiency and the Greek fixed-odds betting market

PurposeThe purpose of this study is to empirically examine the efficiency of Greek fixed-odds (offline) betting market as offered by OPAP for the period 2016–2019.Design/methodology/approachUsing a four-year data sample of OPAP's opening and closing odds for football matches from all over the world and applying linear probability and probit models, the market efficiency is examined and the existence of possible anomalies is investigated.FindingsThe main findings of research suggest that although the odds are dominated primarily by favorite-longshot bias and secondarily by draw bias, this mispricing cannot prove profitable. However, the opening odds, the margin levels and the market structure provide information that is not fully captured by the closing odds, giving bettors profit opportunities. Thus, findings show that the semi-strong market efficiency is questionable. Finally, competition reduces commissions leading to more efficient odds.Practical implicationsThe conclusions of this study are useful for football betting market and, particularly, for government authorities, bookmakers and bettors. Findings can be extended in future research to prediction tasks.Originality/valueTo the best of the authors’ knowledge, this is the first study about the Greek football betting market. The contribution to the literature lies on the one hand in the examination of a monopolistic land-based betting market, which is being squeezed and threatened by the more competitive online betting market, and on the other hand in the simultaneous examination of the opening and closing odds.

Using Convolutional Neural Network and Candlestick Representation to Predict Sports Match Outcomes

The interdisciplinary nature of sports and the presence of various systemic and non-systemic factors introduce challenges in predicting sports match outcomes using a single disciplinary approach. In contrast to previous studies that use sports performance metrics and statistical models, this study is the first to apply a deep learning approach in financial time series modeling to predict sports match outcomes. The proposed approach has two main components: a convolutional neural network (CNN) classifier for implicit pattern recognition and a logistic regression model for match outcome judgment. First, the raw data used in the prediction are derived from the betting market odds and actual scores of each game, which are transformed into sports candlesticks. Second, CNN is used to classify the candlesticks time series on a graphical basis. To this end, the original 1D time series are encoded into 2D matrix images using Gramian angular field and are then fed into the CNN classifier. In this way, the winning probability of each matchup team can be derived based on historically implied behavioral patterns. Third, to further consider the differences between strong and weak teams, the CNN classifier adjusts the probability of winning the match by using the logistic regression model and then makes a final judgment regarding the match outcome. We empirically test this approach using 18,944 National Football League game data spanning 32 years and find that using the individual historical data of each team in the CNN classifier for pattern recognition is better than using the data of all teams. The CNN in conjunction with the logistic regression judgment model outperforms the CNN in conjunction with SVM, Naïve Bayes, Adaboost, J48, and random forest, and its accuracy surpasses that of betting market prediction.

CONSUMER BEHAVIOUR ANALYSIS IN THE SPORTS BETTING MARKET

This paper aims to evaluate the sociological and economic implications that the sports betting industry has over the consumers financial resources and on the psyche of the consumers. The aim of the research is to gather information about the sports bettor’s behaviour, motivations, expectations, his decision-making process, the factors that influence his choices, their perspective about skill and chance and the overall management of the betting activity.

Modeling of Football Match Outcomes with Expected Goals Statistic

Aim. Our research examined the predictive capabilities of mathematical models that are solely based on the expected goal statistics obtained from a publicly available database. Method. We collected match and expected goals data for 310 matches from three European Leagues (Bundesliga, La Liga, and Serie A). We created three probabilistic models based on the expected goals statistic and compared them with two well-established probabilistic models using binomial deviance, squared error, and profitability in the betting market as evaluation metrics. Results. Our best model adjusted the expected goal statistics for homefield advantage and outperformed the two probabilistic models used for comparison. Two of our models were profitable under certain betting conditions. Limitations. Our models explored a simplistic integration of expected goals into a Poisson based probabilistic model and did not include other contributing factors such as a team’s defensive prowess. The number of games simulated was also limited due to the premature closure of the European Leagues due to the COVID-19 pandemic. Conclusions. The use of a probabilistic model based solely on expected goals score statistic can provide some meaningful insight into forecasting the outcome of a football match and can develop useful betting strategies.

Efficiency Testing of Prediction Markets: Martingale Approach, Likelihood Ratio and Bayes Factor Analysis

This paper studies efficient market hypothesis in prediction markets and the results are illustrated for the in-play football betting market using the quoted odds for the English Premier League. Our analysis is based on the martingale property, where the last quoted probability should be the best predictor of the outcome and all previous quotes should be statistically insignificant. We use regression analysis to test for the significance of the previous quotes in both the time setup and the spatial setup based on stopping times, when the quoted probabilities reach certain bounds. The main contribution of this paper is to show how a potentially different distributional opinion based on the violation of the market efficiency can be monetized by optimal trading, where the agent maximizes logarithmic utility function. In particular, the trader can realize a trading profit that corresponds to the likelihood ratio in the situation of one market maker and one market taker, or the Bayes factor in the situation of two or more market takers.