Blogs.

Read about how we are doing, new products, new product features and much more!
Profitable Football Predictions

Profitable Football Predictions

January 29, 2020 15:30 in Soccer

SportMonks Football Predictions API, how to get smarter than bookmakers?

Are you ready to take advantage of our Predictions and make high profits?

In August 2019 we launched the SportMonks Football Predictions API. Based on our own data, using cutting edge Machine Learning and statistical models, our Team of Data scientists has delivered a great innovative product. More than 500 customers have already experienced the ease and profitability of this product. We are very happy with the reactions and feedback so far. This blog will tell you more on how the Predictions API works, what it will provide you, and how you can get started to make profits right away. The past months and the upcoming months our full focus is on improving the model to get better and more predictions for you. For example, we just updated our algorithm with some massive improvements. We expect substantial performance upgrades to many of the League Hit ratio's. Although we are very happy with the performance of the model so far, for some Leagues there is definitely room for improvement. But the good thing for you is, you can easily track for which Leagues the Predictions are very good. Just use this endpoint: https://soccer.sportmonks.com/api/v2.0/predictions/leagues?api_token=__TOKEN__ Be aware you need to have an active subscription to use our API. Get Started Now Completely free to try for the first 14 days. We would like to give you a deeper explanation on how to use the Football Prediction API and Value Bet API for your own application.

How to use the Predictions

The Prediction API comes with several features that help you understand and monitor the performance of the Prediction model. The Value Bet API is available as a complementary feature of the Prediction API. These are two distinct tools that can be used together. I will now try to explain how to use and understand these API's.

The Value Bet API

First, the Value Bet API is independent and thus not related to the Prediction API. While the Prediction API evaluates the probabilities of game events, the Value Bet API is processing thousands of historical odds data and market trends to find Value opportunities, compared against bookmakers odds. Once the opening odds are available, the value detection algorithm is running every 10 minutes up to the beginning of the match. Each value detected by the model is coming with a set of features I will describe below.

The stake feature

Each of the Value Bet detected by the model has a stake. The stake is helping to manage the risk that the model would take in the bet. It is somewhere between the Kelly (1) bet and the Markowitz (2) theory. The risk is measured with the volatility of the profit and loss of the Value Bet Strategy. The stake is calculated in order to have an average risk of one unit (it could be one euro, one dollar...) In order to illustrate this, let's assume one always bets on an event which has 20% of success. The fair odd in this case is 5. If your stake is 3 units, this is mean that in 20% of the time your profit is 12 units and in 80% of the time your loss is -3 units. The volatility and thus the risk of the profit and loss is 6 units in this case. The Value Bet API gives for each value detected the stake that will give you a volatility of 1 unit if the match was played multiple times. This way you own the same risk for every Value in the API found. The maximum allowed stake is 5 units. But it is important to keep this scale the same. If you want to take a risk of 2 (or any number) units in average, you just have to multiply all the stakes by 2 (or any number). In this case the maximum stake will be 10 units.

Introducing the fair odd feature

Our algorithm allows you to find the fair odd of a value. The fair odd is useful to play against bookmakers that are not listed in Sportmonks. Any odd above the fair odd can be considered as Value. In the previous example (fair odd = 5), any odd offered by a random bookmaker above 5 should be taken for a bet.

The Prediction API

The goal of the prediction API is to evaluate the probabilities of a given match using machine learning and statistical methods on our data. Alle Predictions are available 3 weeks forward. This allows you to bet against opening odds for example. To help you track the performance, the API is coming with the league predictability feature. It is a set of metrics that measures the quality and the predictive power of the model.

  1. - hit ratio: number of times the model predicts the right outcome (1, X, 2) over the last 100 matches of the league. The closer to 1,00 the better. The random prediction has a hit ratio of 0.33 (33%).
  2. - log loss: average log loss over the last 100 matches of the league. This is measuring the quality of the probabilities. The closer to 0 the better. Here, the quality is considered as good when is it below -1.02 and high when it is below -0.98. The random prediction has a log loss of -1.09. So any log loss below -1.07 will be considered as poor predictability.
  3. - predictability: not everybody is comfortable with numbers. The predictability tells you in a word if the league has a poor, medium, good or high predictability.
  4. - predictive power: the predictive power tells you if the log loss has been increased since the last 50 matches. It can be up, down or unchanged. When the predictive power is up, the league is becoming more predictable.


Please let us know when you have any feedback or questions for us. Please check here if you need more detailed information about the Football Predictions API. We are putting massive effort in the Football Prediction API and we really need you to improve our products day by day. Be aware that results from the past are no guarantees for the future.

>>> I want to see how an API response of the Predictions API looks

>>> I want to start testing the Value Bet and Prediction API

Are you interested in getting more Football Data like Livescores, (live)Odds, (live)Stats, Fixtures, Standings or any other type Football Data, for 900+ Leagues. Check here, for all our Football offerings

Good luck!

  1. See the Kelly_criterion(1956).
  2. See the mean variance theory(1952).

Build amazing products with realtime sports data.

Get started with our 14-day free trial, and experience blazing fast livescores. Get started