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.     

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.     

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.     

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.     

Odds-setting efficiency in gambling markets: Evidence from the PGA TOUR

This paper describes the gambling market for PGA TOUR events for the 2002 season. The extent to which the odds predict the outcome is examined, illustrating how much information is captured in the odds and whether there are any identifiable biases in the odds. The overall implied profit to the casino is calculated as well as the returns to several naive betting strategies. By splitting the sample based on whether or not Tiger Woods is in the tournament, a “Tiger Woods effect” or a “thin market versus thick market effect” can be examined. On the whole, efficient markets propositions hold up, but the overwhelming share of the variation in the tournament outcome remains unexplained.     

Market efficiency in Scandinavian racetrack betting

This study analyzes Scandinavian racetrack betting markets. We discuss market efficiency and investor behavior in light of the fact that investors earn negative returns on average. Show bets on favorites in Norway yield a small positive return, while all the other betting markets are weak form efficient. We establish the favorite-longshot bias for quinella and exactor bettors, but not for win bettors. Our results can be explained by small pools and high track takes. Investors wagering at the racetrack have a different risk attitude than investors wagering off the track. We explain how our results should influence the design of betting products, especially with respect to the fraction of the pool returned to winners.     

What Do Bettors Want? Determinants of Pari‐Mutuel Betting Preference

A bstract .   This paper is an analysis of the demand for thoroughbred racetrack wagers, examining evidence that would support the existence of two types of bettors: the risk-averse informed bettor versus the uninformed bettor. Looking at 12 major racetracks over the fall of 2002, we undertake an empirical examination of the determinants of bettors' preferences for particular wagers on specific races. The goal is to try to determine what individual aspects of a race (conditions, surface, participants, etc.) will encourage increased wagering dollars. With the advent of simulcasting, the competition for the wagering dollar is fierce, as the bettor can choose from more than 100 races daily, each race offering numerous betting options. We find for most wagers that higher quality participants, larger and more competitive fields, and turf races increase betting volume while higher pari-mutuel takeout, poor track conditions, and other races run concurrently reduce volume. However, more competitive fields reduce betting volume in the show and trifecta pools. Optimal field size is determined to be between 10 and 12 betting interests. Overall, we find support for the existence of a significant share of risk-averse informed bettors.     

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.     

The behaviour of betting and currency markets on the night of the EU referendum

We study the behaviours of the Betfair betting market and the sterling/dollar exchange rate (futures price) during 24 June 2016, the night of the EU referendum. We investigate how the two markets responded to the announcement of the voting results by employing a Bayesian updating methodology to update prior opinion about the likelihood of the final outcome of the vote. We then relate the voting model to the real-time evolution of the market-determined prices as the results were announced. We find that, although both markets appear to be inefficient in absorbing the new information contained in the vote outcomes, the betting market seems less inefficient than the FX market. The different rates of convergence to the fundamental value between the two markets lead to highly profitable arbitrage opportunities.     

Evaluating the conditionality of judgmental forecasts

We propose a framework for evaluating the conditionality of forecasts. The crux of our framework is the observation that a forecast is conditional if revisions to the conditioning factor are incorporated faithfully into the remainder of the forecast. We consider whether the Greenbook, Blue Chip survey and Survey of Professional Forecasters exhibit systematic biases in the manner in which they incorporate interest rate projections into the forecasts of other macroeconomic variables. We do not find strong evidence of systematic biases in the three economic forecasts that we consider, as the interest rate projections in these forecasts appear to be incorporated efficiently into the forecasts of other economic variables.     

The wisdom of large and small crowds: Evidence from repeated natural experiments in sports betting

Prediction markets have proved excellent tools for forecasting, outperforming experts and polls in many settings. But do larger markets, with a wider participation, perform better than smaller markets? This paper analyses a series of repeated natural experiments in sports betting. The Queen’s Club Tennis Championships are held every year, but every other year the Championships clash with a major soccer tournament. We find that tennis betting prices become significantly less informative when participation rates are affected adversely by the clashing soccer tournament. This suggests that measures which increase prediction market participation may lead to a greater forecast accuracy.     

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.     

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.     

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.     

Information flow between prediction markets,polls and media: Evidence from the 2008 presidential primaries

Are the forecast errors of election-eve polls themselves forecastable? We present evidence from the 2008 Democratic Party nomination race between Barack Obama and Hillary Clinton showing that the answer is yes. Both cross-sectional and time series evidence suggests that market prices contain information about election outcomes that polls taken shortly before the contests do not. Conversely, election surprises relative to polls too Granger cause subsequent price movements. We then investigate whether the additional information in prices could come from the media coverage of these campaigns, and uncover a set of complex relationships between pollster’s surprise, price movements, and various aspects of media coverage. Prices anticipate the balance and content of media coverage, but not the volume. On the other hand, it is the volume of media coverage, not the balance or content, that anticipates the surprise element in election outcomes. Moreover, Granger causality between prices and election surprises barely changes after controlling for media coverage, and causality from media volume to surprises persists too after controlling for price movements. Taken together, the results suggest that both prices and the volume of media coverage contain independent election-relevant information that is not captured in polls.     

Beating the market with a bad predictive model

It is a common misconception that in order to make consistent profits as a trader, one needs to possess some extra information leading to an asset value estimation that is more accurate than that reflected by the current market price. While the idea makes intuitive sense and is also well substantiated by the widely popular Kelly criterion, we prove that it is generally possible to make systematic profits with a completely inferior price-predicting model. The key idea is to alter the training objective of the predictive models to explicitly decorrelate them from the market. By doing so, we can exploit inconspicuous biases in the market maker’s pricing, and profit from the inherent advantage of the market taker. We introduce the problem setting throughout the diverse domains of stock trading and sports betting to provide insights into the common underlying properties of profitable predictive models, their connections to standard portfolio optimization strategies, and the commonly overlooked advantage of the market taker. Consequently, we prove the desirability of the decorrelation objective across common market distributions, translate the concept into a practical machine learning setting, and demonstrate its viability with real-world market data.     

考虑市场力的短期边际电价预测

电价波动较负荷波动剧烈,使得整个电价的预测精度降低。造成这种价格波动的主要原因是由于在电力市场中,发电商拥有的市场力具有能够支配电价上下波动的能力,使得电价的变化更加难以预测。因此市场力在电价预测中是必须考虑的重要因素之一。提出将市场供需比指标作为电价预测的一个输入量,将其引入到预测模型中作为影响电价的因素,使预测精度得到提高。     

Real Balances, the Price Level and the Unit of Account

A bstract It is argued that Patinkin's introduction in his 1956 book of the stability analysis of the price level resulted in great measure from his reading of Wicksell's 1898 Interest and Prices. Both Patinkin and Wicksell based their treatments of the stability of the price level on what Patinkin used to call the "real balance effect." That effect, however, does not operate under Wicksell's assumption of a competitive "pure credit economy", where all transactions are carried out by bookkeeping transfers, and the unit of account is the same unit in which the accounts of banks are kept. In that case, Patinkin showed in the second (1965) edition of his book that the real balance effect–and, by that, the stability of the price level–would still be a feature of the system if profit maximizer banks held reserves, created by the central bank to settle temporary imbalances at the clearinghouse. According to Wicksell, on the other hand, a pure credit economy should consist of a central bank that attracts and remunerates deposits at the same interest rate charged for its loans, plus profit maximizer financial intermediaries that lend money for risky projects. The basic rate of interest set by the central bank decides, accordingly, the price level in such an economy. Wicksell's and Patinkin's approaches differ from the view put forward in the 1980s by the so-called "new monetary economics" that the key to price level stabilization is the separation of the function of money as the unit of account from its function as the medium of exchange in pure accounting systems of exchange.     

House Prices, Housing Investment and Demography Forecasts from the LBS/Abbey National Model of the UK Housing Market

A new housing sector has been incorporated into the London Business School model. This article outlines the new housing model, summarizes the research which has gone into its construction, and presents a forecast of the UK housing market. Using the new housing model, we forecast a moderate recovery in the housing market in the later part of 1991 and 1992. This recovery is however short-lived and does not result in such high rates of house price increase as previous house price booms (Chart 1).
Cuts in interest rates following entry to the exchange rate mechanism of the EMS prompt a recovery in house prices from the middle of 1991. House price inflation then peaks with an increase in average UK house prices in 1992 of 11 per cent over the previous year. Increases in real personal disposable income are modest, by the standards of the 1980s, and for this reason the recovery does not develop the momentum of previous house price booms. House price inflation moderates again in 1993 falling back to around 7 per cent. Housing starts and housing investment recover only slightly from their present depressed levels.
the recovery in house prices is weaker than that foreseen in our April Forecast Release. This is because real personal disposable income is now forecast to grow more slowly during 1991. Sterling's membership of the ERM is followed by a fall in interest rates, but it is the timing of interest rate cuts rather than their magnitude which differs from the earlier forecast. The changed profile of interest rates has altered the house price forecast only marginally.     

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.