How to predict an outcome of the game (next row) based on all previous games (rows)?

I'm a data science student and I've come across a fairly unusual dataset (to me, which explains the vague title).

It's of the following form:

Basically, the rows represent the statistics of the current match and at the end of the row the columns NEXT_HOME and NEXT_AWAY represent the teams which are playing the next game (next row) and the result of that next game is stored in NEXT_WINNER.

The test data is of the same form but without the NEXT_WINNER column because that's the target variable.

This is unusual to me because essentially I need to predict the outcome of the next match based on all previous matches using a machine learning model of my choice.

I've never done anything like this so I would appreciate some guidance (not solutions, just advice and where to start). Something of the sort of how to transform the dataset to make it more manageable.

Thanks.