In conclusion, we would expect horses with a higher number of races would have better performance. Thirdly and most importantly, this factor describes how many races the horse has run. To maintain fairness, higher rating horses are carrying more weights. Secondly, The weight that the horse is carrying, including jockey’s weight and extra weight. The below shows the distribution of ratings by race class there are some overlaps in the classifications. Horses are assigned to different race classes based on their ratings in Hong Kong. This could change every race for the same horse. Here are some factors that I think they are fundamentally important:įirstly, The rating of a horse, which is available publicly on websites. Moreover, I think the best approach is to first understand the mechanics of horse racing, so at least understand fundamentally what is important in determining the winner of a race - a “quanta-mental” approach that has been trending in the finance industry. One way to tackle a prediction problem is to throw all the available factors into a machine learning model and hope for the best. 2 racetracks in Hong Kong Horse Racing each racetrack has multiple distances.īelow is a small sample of the tabular data Sample tabular data.The racing season begins after summer each year in September and ends in July.Įach line of data represents one horse in each race and contains all the information about that particular horse, including the market odds. In the current dataset, there are a total of around 1800 races, and each race has 6–14 horses competing.ĭata spans from 2018 to 2021 and contains more than 2 full seasons with sectional times on races. Quartet - 1st, 2nd, 3rd, and 4th in the correct order in the race.First Four - 1st, 2nd, 3rd, and 4th in any order in the race.Tierce - 1st, 2nd, and 3rd in the correct order in the race.Trio - 1st, 2nd, and 3rd in any order in the race.Quinella Place - Any two of the first three placed horses in any finishing order in the race.Quinella - 1st and 2nd in either order in the race.Place - 1st, 2nd, or 3rd in a race with 7 or more declared starters or 1st, 2nd in a race with 4, 5, 6 declared starters.Any machine learning enthusiasts might be able to build a system to bet on horses with an edge over mom and pop bettors.įurther, other than betting on the winning horse, there are also several types of bets for each horse race: There are multiple data sources that provide structured tabular data for each historical race which has hundreds of columns, with an affordable season subscription on where you can get all historical data from a relational horse racing database.Īnother interesting phenomenon is Hong Kong’s pari-mutuel betting pools, that the odds are determined by market forces rather than bookies. One of the great machine learning problems is the availability of data. In this article, we are going to describe what makes machine learning a great element for beating public betting odds on horse racing.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |