Fair bets and profitability in college football gambling

Efficient markets in college football are tested over a 25-year period, 1976–2000. the market in general is found to be efficient, but betting on underdogs of more than 28 points violates a fair bet. The strategy of betting home underdogs reveals stronger results. Home underdogs of more than seven points are found to reject the null hypotheses of a fair bet over the last 10 years of the sample, 1991–2000. Home underdogs of more than 28 points are found to reject the null of no profitability during the same time frame.     

Forecasting football results and exploiting betting markets: The case of “both teams to score”

The continuous growth of available football data presents unprecedented research opportunities for a better understanding of football dynamics. While many research works focus on predicting which team will win a match, other interesting questions, such as whether both teams will score in a game, are still unexplored and have gained momentum with the rise of betting markets. With this in mind, we investigate the following research questions in this paper: “How difficult is the ‘both teams to score’ (BTTS) prediction problem?”, “Are machine learning classifiers capable of predicting BTTS better than bookmakers?”, and “Are machine learning classifiers useful for devising profitable betting strategies in the BTTS market?”. We collected historical football data, extracted groups of features to represent the teams’ strengths, and fed these to state-of-the-art classification models. We performed a comprehensive set of experiments and showed that, although hard to predict, in some scenarios it is possible to outperform bookmakers, which are robust baselines per se. More importantly, in some cases it is possible to beat the market and devise profitable strategies based on machine learning algorithms. The results are encouraging and, besides shedding light on the problem, may provide novel insights for all kinds of football stakeholders.     

Bettor preferences and market efficiency in football totals markets

The betting markets for totals in college football and arena football provide additional evidence of bettor preference for scoring. The results for college football and arena football markets are similar to those found in the professional football and professional basketball totals market. In all of these leagues, the overs are overbet. We suggest that there is a clear preference for bettors to bet the over and the extent of the bias depends upon the volume of uninformed bettors to informed bettors and limits placed on bets in these markets.     

Exploiting sports-betting market using machine learning

We introduce a forecasting system designed to profit from sports-betting market using machine learning. We contribute three main novel ingredients. First, previous attempts to learn models for match-outcome prediction maximized the model’s predictive accuracy as the single criterion. Unlike these approaches, we also reduce the model’s correlation with the bookmaker’s predictions available through the published odds. We show that such an optimized model allows for better profit generation, and the approach is thus a way to ‘exploit’ the bookmaker. The second novelty is in the application of convolutional neural networks for match outcome prediction. The convolution layer enables to leverage a vast number of player-related statistics on its input. Thirdly, we adopt elements of the modern portfolio theory to design a strategy for bet distribution according to the odds and model predictions, trading off profit expectation and variance optimally. These three ingredients combine towards a betting method yielding positive cumulative profits in experiments with NBA data from seasons 2007–2014 systematically, as opposed to alternative methods tested.     

Forecasting football match results in national league competitions using score-driven time series models

We develop a new dynamic multivariate model for the analysis and forecasting of football match results in national league competitions. The proposed dynamic model is based on the score of the predictive observation mass function for a high-dimensional panel of weekly match results. Our main interest is in forecasting whether the match result is a win, a loss or a draw for each team. The dynamic model for delivering such forecasts can be based on three different dependent variables: the pairwise count of the number of goals, the difference between the numbers of goals, or the category of the match result (win, loss, draw). The different dependent variables require different distributional assumptions. Furthermore, different dynamic model specifications can be considered for generating the forecasts. We investigate empirically which dependent variable and which dynamic model specification yield the best forecasting results. We validate the precision of the resulting forecasts and the success of the forecasts in a betting simulation in an extensive forecasting study for match results from six large European football competitions. Finally, we conclude that the dynamic model for pairwise counts delivers the most precise forecasts while the dynamic model for the difference between counts is most successful for betting, but that both outperform benchmark and other competing models.     

Regional information and market efficiency: the case of spread betting in United States college football

Using game results over a seven year span (1999–2006), we find that United States college football teams in arid regions “win” against the spread in 56.64% of games in which they host a team from a humid region. This result provides statistically significant evidence for both weak and strong form inefficiency in the spread betting markets of such games. By examining other cases of intraregional and interregional competition within the sport, we conclude that this inefficiency does not arise from the effects of travel or home field advantage. Rather, the result indicates that climate aridity is an observed characteristic for which college football betting markets do not accurately control. It is quite rare to find strong form market inefficiency arise from a single variable rather than from an elaborate, multivariable betting strategy. Therefore, the effect of climate aridity upon college football spread betting market efficiency can be characterized as dramatic. It is conjectured that remote market participants may need to “experience” certain types of relevant regional information, such as climate, to act in a market efficient manner.     

Market efficiency and NCAA college basketball gambling

The betting market for NCAA college basketball is examined from the 1996–97 season through 2003–04. In the overall sample, market efficiency cannot be rejected. For big favorites, specifically those favorites of 20 or more, a simple strategy of betting the underdog in these games is shown to reject the null hypothesis of a fair bet since the underdog wins more than implied by efficiency. This bias appears to be the same as in other sports. The home-team bias in college basketball is shown to be the opposite of the other sports, however, since big favorites win more often than implied by efficiency. Potential reasons for this bias such as NCAA tournament incentives and uniformity of playing conditions are discussed.     

Efficiency of online football betting markets

This paper evaluates the efficiency of online betting markets for European (association) football leagues. The existing literature shows mixed empirical evidence regarding the degree to which betting markets are efficient. We propose a forecast-based approach for formally testing the efficiency of online betting markets. By considering the odds proposed by 41 bookmakers on 11 European major leagues over the last 11 years, we find evidence of differing degrees of efficiency among markets. We show that, if the best odds are selected across bookmakers, eight markets are efficient while three show inefficiencies that imply profit opportunities for bettors. In particular, our approach allows the estimation of the odds thresholds that could be used to set profitable betting strategies both ex post and ex ante.     

Additional evidence of heuristic-based inefficiency in season wins total betting markets: Major League Baseball

The large majority of sports betting papers have addressed questions of market efficiency based on the outcome of single game, such as spread (sides) or point totals wagers. This research examines the Major League Baseball (MLB) season wins total over/under betting market with respect to questions of market efficiency and profitability. Woodland and Woodland (2013, 2015) investigated the season wins total markets for the National Football League (NFL) and the National Basketball Association (NBA) and found significant inefficiencies. Betting rules tested in this paper parallel those proposed by Woodland and Woodland for the NFL and NBA. They aim to take advantage of the implications of the representativeness heuristic, that is, individuals expect results from a small number of games to generalize to the entire population. The MLB market is found to be inefficient, and provides opportunities for profitable wagering. We establish a tendency for bettors to overreact to a team’s performance in the previous season, particularly for teams with winning records. Results are consistent with the findings for the NFL and NBA season wins totals betting markets. This may be the consequence of monetary betting limits and a structure requiring the completion of a sport’s season before the bet outcome is determined, both of which could discourage some bettors from participating.     

Informational efficiency and behaviour within in-play prediction markets

Studies of financial market informational efficiency have proven burdensome in practice, because it is difficult to pinpoint when news breaks and is known by some or all the participants. We overcome this by designing a framework to detect mispricing, test informational efficiency and evaluate the behavioural biases within high-frequency prediction markets. We demonstrate this using betting exchange data for association football, exploiting the moment when the first goal is scored in a match as major news that breaks cleanly. There are pre-match and in-play mispricing and inefficiency in these markets, explained by reverse favourite-longshot bias (favourite bias). The mispricing tends to increase when the major news is a surprise, such as a goal scored by a longshot team late in a match, with the market underestimating their chances of going on to win These results suggest that, even in prediction markets with large crowds of participants trading state-contingent claims, significant informational inefficiency and behavioural biases can be reflected in prices.     

Match‐Fixing in a Monopoly Betting Market

A monopolist bookmaker may set betting odds on a fairly even contest to induce match‐fixing by an influential corrupt punter. His loss to the corrupt punter is more than made up for by enticing enough ordinary punters to bet on the losing team. This result is in sharp contrast to competitive bookmaking, where even contests have been shown to be immune to fixing. The analysis also reveals a surprising result that the incidence of match‐fixing can dramatically fall when match‐fixing opportunities rise. This is shown by comparing two scenarios—when only one team is corruptible and when both are corruptible. For both teams corruptible, the bookmaker is uncertain about to which team the influential punter will have access, so carefully maneuvering the odds to induce match‐fixing is too costly.     

A calibration method with dynamic updates for within-match forecasting of wins in tennis

In-match predictions of player win probabilities for professional tennis matches have a wide range of potential applications, including betting, fan engagement, and performance evaluation. The ideal properties of an in-play prediction method include the ability to incorporate both useful pre-match information and relevant in-match information as the match progresses, in order to update the pre-match expectations. This paper presents an in-play forecasting method that achieves both of these goals by combining a pre-match calibration method with a dynamic empirical Bayes updating rule. We present an optimisation rule for guiding the specifications of the dynamic updates using a large sample of professional tennis matches. We apply the results to data from the 2017 season and show that the dynamic model provides a 28% reduction in the error of in-match serve predictions and improves the win prediction accuracy by four percentage points relative to a constant ability model. The method is applied to two Australian Open men’s matches, and we derive several corollary statistics to highlight key dynamics in the win probabilities during a match.     

Sportsbook pricing and the behavioral biases of bettors in the NHL

The betting market for the NHL is investigated using actual betting percentages on favorites and underdogs from real sportsbooks. Sportsbooks do not appear to attempt to price to balance the book as betting percentages are not proportional to set odds. As in the NFL and NBA, bettors are shown to have a strong preference for favorites and road favorites in particular. Simple strategies of betting against significant imbalances toward the favorite are shown to generate positive returns. Although not pricing to balance the book, sportsbooks do not appear to price to exploit known bettor biases in all cases. Clear bettor behavioral biases for road favorites are not priced into the odds as the prices set in these cases appear to be a forecast of game outcomes. Pricing as a forecast may ensure long-run viability for the sportsbook as it discourages entry into this market by informed traders and still allows the sportsbook to capture its commission on losing bets over time.     

Predictive analysis and modelling football results using machine learning approach for English Premier League

The introduction of artificial intelligence has given us the ability to build predictive systems with unprecedented accuracy. Machine learning is being used in virtually all areas in one way or another, due to its extreme effectiveness. One such area where predictive systems have gained a lot of popularity is the prediction of football match results. This paper demonstrates our work on the building of a generalized predictive model for predicting the results of the English Premier League. Using feature engineering and exploratory data analysis, we create a feature set for determining the most important factors for predicting the results of a football match, and consequently create a highly accurate predictive system using machine learning. We demonstrate the strong dependence of our models’ performances on important features. Our best model using gradient boosting achieved a performance of 0.2156 on the ranked probability score (RPS) metric for game weeks 6 to 38 for the English Premier League aggregated over two seasons (2014–2015 and 2015–2016), whereas the betting organizations that we consider (Bet365 and Pinnacle Sports) obtained an RPS value of 0.2012 for the same period. Since a lower RPS value represents a higher predictive accuracy, our model was not able to outperform the bookmaker’s predictions, despite obtaining promising results.     

Interpretable sports team rating models based on the gradient descent algorithm

We introduce several new sports team rating models based on the gradient descent algorithm. More precisely, the models can be formulated by maximising the likelihood of match results observed using a single step of this optimisation heuristic. The proposed framework is inspired by the prominent Elo rating system, and yields an iterative version of ordinal logistic regression, as well as different variants of Poisson regression-based models. This construction makes the update equations easy to interpret, and adjusts ratings once new match results are observed. Thus, it naturally handles temporal changes in team strength. Moreover, a study of association football data indicates that the new models yield more accurate forecasts and are less computationally demanding than corresponding methods that jointly optimise the likelihood for the whole set of matches.     

Wage against the machine: A generalized deep-learning market test of dataset value

How can you tell whether a particular sports dataset really adds value, particularly with regard to betting effectiveness? The method introduced in this paper provides a way for any analyst in almost any sport to attempt to determine the additional value of almost any dataset. It relies on the use of deep learning, comprehensive historical box score statistics, and the existence of betting markets. When the method is applied as an illustration to a novel dataset for the NBA, it is shown to provide more information than regular box score statistics alone, and appears to generate above-breakeven wagering profits.     

On determining probability forecasts from betting odds

We show that the probabilities determined from betting odds using Shin’s model are more accurate forecasts than those determined using basic normalization or regression models. We also provide empirical evidence that some bookmakers are significantly different sources of probabilities in terms of forecasting accuracy, and that betting exchange odds are not always the best source, especially in smaller markets. The advantage of using Shin probabilities and the differences between bookmakers decrease with an increasing market size.     

Keeping a weather eye on prediction markets: The influence of environmental conditions on forecasting accuracy

Increasingly, prediction markets are being embraced as a mechanism for eliciting and aggregating dispersed information and providing a means of deriving probabilistic forecasts of future uncertain events. The efficient market hypothesis postulates that prediction market prices should incorporate all information that is relevant to the performances of the contracts traded. This paper shows that such may not be the case in relation to information regarding environmental factors such as the weather and atmospheric conditions. In the context of horserace betting markets, we demonstrate that even after the effects of these factors on the contestants (horses and jockeys) have been discounted, the accuracy of the probabilities derived from market prices is affected systematically by the prevailing weather and atmospheric conditions. We show that significantly better forecasts can be derived from prediction markets if we correct for this phenomenon, and that these improvements have substantial economic value.     

Betting on a buzz: Mispricing and inefficiency in online sportsbooks

Bookmakers sell claims to bettors that depend on the outcomes of professional sports events. Like other financial assets, the wisdom of crowds could help sellers to price these claims more efficiently. We use the Wikipedia profile page views of professional tennis players involved in over 10,000 singles matches to construct a buzz factor. This measures the difference between players in their pre-match page views relative to the usual number of views they received over the previous year. The buzz factor significantly predicts mispricing by bookmakers. Using this fact to forecast match outcomes, we demonstrate that a strategy of betting on players who received more pre-match buzz than their opponents can generate substantial profits. These results imply that sportsbooks could price outcomes more efficiently by listening to the buzz.     

The value of statistical forecasts in the UK association football betting market

In this paper, we evaluate the economic significance of statistical forecasts of UK Association Football match outcomes in relation to betting market prices. We present a detailed comparison of odds set by different bookmakers in relation to forecast model predictions, and analyse the potential for arbitrage across firms. We also examine extreme odds biases. A detailed re-examination of match result odds and a new examination of correct score odds for the period 1993 to 1996 suggest that the market is inefficient.