1

Using Machine Learning How to recognise a pattern in a data without using data visualisation so that the machine recognises patterns on its own so I can use those patterns for further analysis without needing to analyse visualisations on my own ?

Patters as: the pattern of my sales in different months, years or weeks, pattern of the attendance of a particular student in school, patter on the websites being viewed each month, year, week....

So patterns as such need to be identified by the machine (via Unsupervised learning I guess) and without using graphs, charts or any kind of visualisation

Can you tell me if that's do-able ? If yes, then how ?

Nelson D'souza
  • 51
  • 6

1 Answers1

1

If I understand your question in the right way you are having time series of data (i.e. value of something on a certain date-time point) within which you want to find some patterns.

If you are new to this area and you want to use very simplistic approach which you would definitely understand I would suggest you to write very simple script based on percent change - this will normalise your results and create patterns as well.

x = ((float(currentPoint) - startPoint) / abs(startPoint)) * 100.00

If there is any chance your startPoint can be equal to zero wrapt that in try-except. Then you should determine how long should your patterns be and how you want to choose that the pattern is significant/important for you. All the ideas and code examples could be find here https://pythonprogramming.net/machine-learning-pattern-recognition-algorithmic-forex-stock-trading/

Petr Matuska
  • 553
  • 5
  • 15