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.     

Team Learning from Mistakes: The Contribution of Cooperative Goals and Problem‐Solving*

ABSTRACT Although mistakes may have considerable potential for learning, previous research has emphasized that organizational members are often defensive when their mistakes are pointed out and will even continue with their present course of action despite growing costs. Recent research has shown that team‐level variables, such as psychological safety and shared mental model, can help overcome barriers to learning from mistakes. Structural equation analyses on teams working in a sample of organizations in Shanghai, China, suggested that teams were able to learn from their mistakes to the extent that they took a problem solving orientation. This orientation in turn was based on developing cooperative but not competitive goals within the team. Although competitive and independent goals induce blaming, blaming itself was not significantly related to learning. Blaming, especially when conducted openly, may hold individual team members accountable as well as provoke defensiveness. Findings empirically link the theory of cooperation and competition with the organizational learning literature. Results suggest that cooperative goals and problem solving promote learning from mistakes.     

Self‐managed work teams: An efficiency‐rationale for pay compression

This paper uncovers a novel mechanism through which pay dispersion can have a negative effect on firm performance, even in the absence of equity or fairness considerations. We use a stylized model of a self‐managed work team to show that, when team‐work involves heterogeneous tasks, the provision of incentives to exert effort conflicts with the provision of incentives to share information relevant for decision‐making. Pay dispersion deteriorates information sharing as it induces workers to conceal “bad news” to maintain their coworkers motivation. The practical implications of our theory are that team empowerment should go hand in hand with pay compression and that empowerment should be avoided when team production involves strongly heterogeneous tasks.     

Stadium attendance and television audience demand in English league football

Demand studies of professional team sports have traditionally focused on stadium attendance; however, advances in broadcasting mean that teams generate revenue from stadium goers and broadcasters alike. Previous studies of demand have focused on stadium attendance and television audiences, but none have assessed the demand for match‐day attendances and demand by television audiences jointly. This study models match‐day attendances and television audiences using data from tier‐two of English league football. It shows that while televised matches depress stadium attendances, ceteris paribus, there is an important feedback in that larger stadium attendances have positive impacts on the size of television audiences. Copyright © 2007 John Wiley & Sons, Ltd.     

Equal Pay for Unequal Work: Limiting Sabotage in Teams

We demonstrate the value of "equal pay" policies in teams, even when team members have distinct abilities and make different contributions to team performance. A commitment to compensate all team members in identical fashion eliminates the incentive that each team member otherwise has to sabotage the activities of teammates in order to induce the team owner to implement a more favorable reward structure. The reduced sabotage benefits the team owner, and can secure Pareto gains under plausible circumstances.     

Do Individual Preferences Affect the Environmental Decision‐Making Process in Teams? The Role of Participation

Literature on organizations and the natural environment has focused on the importance of individual managers and leaders. However, this literature has scarcely ever focused on individuals in the team context, even when teams have been considered to be key for a firms’ environmental progress. Although teams’ environmental decisions can be enriched by the different contributions of team members, it is necessary that team members actually participate and contribute their preferences during the decision‐making process. We used an adaptation of the legislative dilemma task with 84 students to contribute to environmental management literature by analyzing members’ participation during the team decision‐making process. The results of this paper show how those members with environmentally proactive preferences have a higher participation during the decision‐making process, and as a consequence they have a greater influence on the team decision. Copyright © 2013 John Wiley & Sons, Ltd and ERP Environment.     

Open-mindedness in diverse team performance: investigating a three-way interaction

Studies have shown that open-minded dynamics contribute to diverse team effectiveness; however, there are few studies on the factors that influence the impact of open-mindedness. Survey data from 218 members of 47 professionally diverse teams support a significant relationship between open-mindedness and performance. Professional identification and professional salience were found to moderate the relationship with opposing effects. The study data indicate that although open-mindedness provides a context that facilitates the open exchange and discussion of diverse ideas and perspectives in interprofessional teams, this is less influential when members strongly identify with their profession. Conversely, member focus on professional differences enhances the value of team interaction characterised by receptiveness and openness. Analysis confirms a three-way interaction between open-mindedness, professional identification and salience on performance.     

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.     

Team Incentives and Reference‐Dependent Preferences

We investigate a multi‐agent moral‐hazard model where agents have expectation‐based reference‐dependent preferences à la K?szegi and Rabin (2006, 2007). We show that even when each agent's probability of success in a project is independent, a principal may employ team incentives. Because the agents are loss averse, they have first‐order risk aversion to wage uncertainty. This causes the agents to work harder when their own failure is stochastically compensated through other agents' performance. In the optimal contract, agents with high performance are always rewarded, whereas agents with low performance are rewarded if and only if other agents' performance is high.     

Relay the Right Way: Harnessing Heterogeneity in Sequential Team Production

How a manager chooses to organize teams is a question with substantial efficiency implications. This study reports evidence on how ordering of heterogenous team members impacts productivity and free riding in a sequential production task. A laboratory experiment permits exogenous reordering of team members by cost of contribution. Analyses suggest that team productivity is higher when low cost team members lead and less variable when low cost members both precede and follow high cost members (e.g., the conventional relay team order). Additionally, team members are found to respond in‐kind to the contributions of both predecessors and successors. Copyright © 2015 John Wiley & Sons, Ltd.     

Hiring for Networks: Social Capital and Staffing Practices in Transitional China

This article investigates how firms’ use of social capital criteria in staffing practices has been affected by China's transitional institutional environment and explores the impacts of person‐job fit in the social capital dimension on employees’ performance. Empirical results show that non‐state‐owned enterprises set a higher social capital standard in the hiring process than state‐owned enterprises. Foreign‐invested enterprises outperform other firms in promoting a better match between individuals rich in social capital and the positions that need such resources. In places with intensive market competition, foreign and private enterprises pay even more attention to employees’ social capital when making HR decisions. Moreover, a better match between people and positions from a social capital aspect has a positive impact on employees’ performance. Theoretical and managerial implications are discussed. © 2015 Wiley Periodicals, Inc.     

A profitable model for predicting the over/under market in football

The over/under 2.5 goals betting market allows gamblers to bet on whether the total number of goals in a football match will exceed 2.5. In this paper, a set of ratings, named ‘Generalised Attacking Performance’ (GAP) ratings, are defined which measure the attacking and defensive performance of each team in a league. GAP ratings are used to forecast matches in ten European football leagues and their profitability is tested in the over/under market using two value betting strategies. GAP ratings with match statistics such as shots and shots on target as inputs are shown to yield better predictive value than the number of goals. An average profit of around 0.8 percent per bet taken is demonstrated over twelve years when using only shots and corners (and not goals) as inputs. The betting strategy is shown to be robust by comparing it to a random betting strategy.     

An experimental test of behavior under team production

This study reports experiments that examine behavior under team production and a piece rate. In the experiments, participants complete a forecasting task and are rewarded based on the accuracy of their forecasts. In the piece‐rate condition, participants are paid based on their own performance, whereas the team‐production condition rewards participants based on the average performance of the team. Overall, there is no statistically significant difference in performance between the conditions. However, this result masks important differences in the behavior of men and women across the conditions. Men in the team‐production condition increase their performance relative to men in the piece‐rate condition. However, this gap in male performances across conditions diminishes over the course of the experiment. In contrast, women in the team‐production condition show significantly lower performance than the women in the piece rate. As a consequence of these differences, men in the team‐production condition show significantly better performance than women in the team‐production condition. We also find evidence that men show stronger performance when they are in teams with a larger variation in skill level. Copyright © 2010 John Wiley & Sons, Ltd.     

Estimating Precision and Recall for Deterministic and Probabilistic Record Linkage

Linking administrative, survey and census files to enhance dimensions such as time and breadth or depth of detail is now common. Because a unique person identifier is often not available, records belonging to two different units (e.g. people) may be incorrectly linked. Estimating the proportion of links that are correct, called Precision, is difficult because, even after clerical review, there will remain uncertainty about whether a link is in fact correct or incorrect. Measures of Precision are useful when deciding whether or not it is worthwhile linking two files, when comparing alternative linking strategies and as a quality measure for estimates based on the linked file. This paper proposes an estimator of Precision for a linked file that has been created by either deterministic (or rules‐based) or probabilistic (where evidence for a link being a match is weighted against the evidence that it is not a match) linkage, both of which are widely used in practice. This paper shows that the proposed estimators perform well.     

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.     

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.     

Training match and mismatch as a driver of key employee behaviours

Training is widely believed to have the potential to improve key workplace outcomes such as the in‐role behaviours and organisational citizenship of employees. However, this article argues that match of actual training provision to requirements leads to the greatest possible improvement in key behaviours, an assertion that lacks prior validation. Undertraining relative to requirements would typically be associated with lower behavioural gain, or even negative behaviours. Overtraining may have both positive and negative implications; however, this article argues that on aggregate excess training will be associated with worse outcomes compared with match. An analysis of 699 matched employee–manager dyads supports the assertion that match is associated with the best relative levels of key workplace behaviours, and associates either undertraining or overtraining with degradation in outcomes. This research highlights the importance of training needs analysis and encourages active management of trained workers to match work to skills.     

Leader productivity and people orientations for cooperative goals and effective teams in China

Researchers have traditionally distinguished leaders by the extent to which they are oriented to people and productivity, and meta-analytic results indicate that these orientations have consistent and practically important effects. But research is needed to understand the dynamics by which these orientations induce team effectiveness. This study empirically relates leader orientations to teamwork by suggesting that productivity- and people-oriented leaders develop cooperative goals among team members that in turn results in team effectiveness. A total of 146 team leaders from 21 organizations in China completed measures of productivity and people orientations and their encouraging cooperative goals among team members; 1067 team members rated their effectiveness. Results of the structural equation analysis support the theorizing that leader productivity and people values when complemented by strengthening cooperative relationships can contribute to making teams effective in China and perhaps in other countries as well.     

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.     

Team performance and managerial change in the English Football League

This paper investigates the relationship between team performance and managerial change in English football using a data set containing information on all match results and managerial job changes in the English Football League between 1972 and 1993. We find that poor recent form drives many managerial terminations, while managerial turnover is more rapid in the lower divisions.
Significantly, managerial change appears to have a harmful effect on team performance immediately following a managerial termination.