Deep learning and horse race prediction #1

By putting money on jockey or horse? TRACK WINS The higher you weight this value the more it will favour horses that have performed well at the track If you put stock in the expression 'horses for courses' then this is the factor for you. As I write this I am not sure if it is going to be a single article or a series. Full Specifications

Predictor FAQs

Predictor - Punters App

As I write this I am not sure if it is going to be a single article or a series. It depends on how the rest of this article goes and more importantly the response to it. To start I think it is appropriate to explain exactly what this theorem is. That gives us an underlying knowledge of what it will help us to achieve and how we can use it in horse racing.

As with most statistics this was not invented specifically to help us make more profits from betting at the races, it was invented as a statistical method of working out probabilities. If you want a more detailed explanation then checkout wikipedia, but we do not need to know more for our purposes. With this knowledge we can see that the purpose of using this in horse racing is to create a probability for each horse in a race using a repeatable method that does not rely in any form on gut instinct.

The way this method of creating a probability work is that it starts off with each horse being given the same chance of winning a race. As more information is added to the model these probabilities increase or decrease relevant to the what the information has told us about a runner.

The secret ingredient is how we add the information in a way that allows us to adjust the probabilities for each runner relevant to what the information has told us. We do this by using something known as likelihood ratios. Working out these ratios is very simple. We decide what information we are going to add, for example last time out winner, and take all the horses we have in our historic races and split them into two groups:.

We then break each of these two groups down into two more groups where are:. This is all the information that we need to create our likelihood ratios. And if you can get this information and have a normal calculator to hand, then you can create probabilities for horses in a race without any difficulty. Doing so is going to allow you to create odds lines and probabilities in the same way that big bettors and major teams do!

Chosen which factors you want to use to create your probabilities and odds lines no more than four or five to start. If you would like to see me do a real sample next week with real data that you can put to use, then leave a comment below with you vote what factors you would like us to use. I have worked with many of the best betting tipsters in the UK, professional punters and also big football syndicates. I think the algorithm or method you're looking for would be akin to the holy grail and to all intents and purpose I am sure it is as good as impossible to create.

The reason is that you are talking about a dynamic activity involving human beings and horses where the key information will always be obscure at best and likely unknowable in advance of each race. Is this the day that every runner is going to put its best foot forward? What runners and riders are in primed condition and what not? And of course, is today's race what it appears to be ie is the race straight or bent? In a game where everyone is trying to hide their intentions for personal gain and advantage data is not the issue.

What is the key component governing success is how that data form is interpreted by very experienced people with very, very good eyes and that indefinable X Factor in their method - something that understands the shades of grey as much as what's black and white. That's people that understand the rules and the exceptions to the rules too because no two betting opportunities are ever exactly the same regardless of superficial similarities.

I have never seen a computer modelled system make anything other than short term gains before blowing up. The best people I've seen know what their watching, know how to interprete it and rely on being more right than wrong over the long term at odds that are greater than the real chance of their selections winning the concept called value betting.

Mostly they rely on their eyes, their ears and the kind of hard-won experience that computers can't have. But lets assume you could build this super-algorithm and it worked.

Who would take your bets and in what sort of stakes and volume? Even if you could plan an orchestrated one day military precision blitz on the bookmakers with cash, or with new clean accounts they would simply cry foul and refuse to pay your winnings out. And let's face it if your algorithm really was the holy grail it would like some sort of corruption was taking place on your part.

I would suggest starting with just the basics. Most tracks now track each runner in real time with electronic trackers. The two most significant aspects to take into account would be 1 total distance covered and 2 total finishing time. Once this information is compared the two most important factors to consider are: Career Best Performance and Recent Form. I have deliberately chosen to overlook the post position barrier stall as the total distance covered is a more appropriate gauge.

Not to imply that these are irrelevant but these will have to be taken into consideration subjectively on a race by race basis. I think the above will be a good starting point in devising an algorithm and covers most of the vital aspects.

This page may be out of date. Save your draft before refreshing this page. Submit any pending changes before refreshing this page. Ask New Question Sign In. What would be a good method or algorithm to predict the winner of a horse race, given a large set of information on horse races? ML workstations — fully configured. Let us save you the work. Our machine learning experts take care of the set up.

Learn More at lambdal. You dismissed this ad. The feedback you provide will help us show you more relevant content in the future. Get hand-matched with proven, senior-level AI engineers for your team. Start Now at toptal. Can bayesian theory be applied to horse racing?

Login or create an account to post a review. The posting of advertisements, profanity, or personal attacks is prohibited. Click here to review our site terms of use. If you believe this comment is offensive or violates the CNET's Site Terms of Use , you can report it below this will not automatically remove the comment. Once reported, our staff will be notified and the comment will be reviewed.

Overview User Reviews Specs. Reviews Current version All versions. Sort Date Most helpful Positive rating Negative rating. Results 1—2 of 2 1. Pros goto there web page and you have to look for stuff to read about the software, there is so little of it, however what there is, sounds pretty darn good, I will continue to back the predictions, however be careful of this.

Cons You feel your not in control, they send you a few horses to back, that's it, even a hello would be nice.. Summary Very simple, Cons as i said above how can someone put a software program up for download on the internet,and not have it in working order. Reply to this review Was this review helpful? You are logged in as. Please submit your review for Horse Racing Predictor. Thank You for Submitting Your Review,!