I have a machine learning project to calculate a probability for the next value in a series.
Given the vectors:
v1 -> [ 1000, 200, -500 ... ]
v1_inverse -> [ -900, -100, 1800 ... ]
Calculate the probability of v1[n] >= 0.
It'll need to be written in a scripting language such as R or Python.
- how do you calculate how much data you need?
- how do you prevent over-fitting?
- what experience do you have with machine learning?
Also please explain how you intend to solve this problem (models, selection, validation etc.)