Relative Content

Tag Archive for machine-learning

which data will be used for Football prediction model

I am planning to create a model to predict football match outcomes using various machine learning techniques. The columns of the collected data include Home, Away, Home Team Goals, Away Team Goals, Home Team Possession, Away Team Possession, Home Team Shots on Target, Away Team Shots on Target, etc. While it seems straightforward to use this data to predict match outcomes, these figures are only available after the match has ended. I believe we should use data that is available before the match, such as club value, points, and recent match results, to make predictions. Therefore, I want the columns of the training data to include both match data and pre-match data, and I want to make predictions using pre-match data. I am also curious about what this concept is called in machine learning.

Wrong machine learning predictions at every run

I trained a machine learning model, and a few of the same rows (around 100 out of 1800) in my test set are giving wrong predictions at every run (10 times) with different seeds. Is there anything I should do about it e.g. throw it in the train set in exchange for some data from the train set to test set or leave it as it is?