Mathfi-Gaming © 
Classifier/Predictive AI


     Log in/Register                Request a Demo                Instruction Manual

A new AI-powered service helping gaming enthusiasts and experts to make better informed decisions whenever a binary or multi-class prediction or classification is required. For example:

1. Predict which team will be the winner of this round of a well-known online multi-player tactical first-person shooter game: As an example, please consider a very well-known online global leader of multi-player tactical first-person shooter competitive games where two teams play for a best of N rounds. Knowing the data features and statistics of thousands of past rounds including time left to the end of game, number of alive plyers of each team at that time and their locations on the maps, type and number of armours each team have, the money left for each team, type and number of weapons each playing team have and many other relevant data features at that specific time of this round, and knowing which team have managed to win that past round (the label and target of prediction), for a new round of the game with known data features predict which team will be the future winner (and with what probability).

2. Predict winner team of this round of the popular online video game (for example the global leader of eSports MOBA games):  Imagine we have statistics of thousands of past rounds of the game when we were 15 minutes into the game. Two blue and red teams were competing. The statistics contain performance data features of both blue and red teams including amount of gold owned, number of minions killed, number of jungle minions killed, the average level of performance, number of champ kills, number of herald kills, number of dragons kills, number of towers destroyed. In addition, we also whether blue team was the winner of any of those past rounds (target and label of prediction). Now for a new round of the game, when we are 15 minutes into the game, predict whether the blue team will win this round or not (and with what probability).
3. Games Recommendations: Knowing past history of game players, category of game, operating system, type of device, game reviews viewed, platform, response to past game recommendations, game reviews submitted, favourite game brands, number of wins, days of week and day the player usually plays, frequency they play the game, gender, age, demographics, location, credit rating, job, income, and other relevant data features and knowing what games they usually play (the target and label to be predicted and recommended), for a new potential player with known data features predict and recommend the game they will most likely subscribe to and play (and with what probability).

Or any other binary or multi-class prediction or classification use cases required by game players and experts to make decisions.

                Log in/Register                Request a Demo                Instruction Manual