How to choose/calculate context in order to get better result?

In the code of this repo, context matrix of shape [batch_size, mem_size] is chosen randomly as below
`
m = random.randrange(self.mem_size, len(data))
target[b][data[m]] = 1
context[b] = data[m - self.mem_size:m]
`
My quesiton (I am sorry it is not actually an 'issue' but my personal quesion) is what approaches I can take to get better result rather than just random?
Any kind of material that is helpful is welcomed :)

Locate the training code containing the random context selection and inspect how the context matrix, target, and data sequence are used. Review the repository's memory-network implementation and relevant training or evaluation entry points before deciding what alternative context-selection approach could be evaluated. Done would require a defined approach and evidence that it improves results.

Written by the indexing model from the issue text.