Question



First Prediction Wednesday Model

Dr. Ballings,

For Wednesday, are we supposed to use one of the ML algorithms we've gone over in the last week (kNN or Naive Bayes)?

Or do you simply want us to be able to give a ranking order of the best stocks that increase by 1%, that will be effected by adding in the
new data you give us Wednesday?

So do you want us to build a model based on the data right now that ranks the stocks that increase day to day by at least 1% that will
output the ranking order based on the stocks that increase by 1% the most number of times, and this model should be able to easily change
Wednesday when you provide us additional data?

Thanks,
Michael





Answers and follow-up questions





Answer or follow-up question 1

Dear Michael:

"For Wednesday, are we supposed to use one of the ML algorithms we've gone over in the last week (kNN or Naive Bayes)?"

Yes.


"Or do you simply want us to be able to give a ranking order of the best stocks that increase by 1%,
that will be effected by adding in the new data you give us Wednesday?"

No.

"So do you want us to build a model based on the data right now that ranks the stocks that increase day to day by at
least 1% that will output the ranking order based on the stocks that increase by 1% the most number of times,
and this model should be able to easily change Wednesday when you provide us additional data?"

The goal is to predict which stocks will go up by 1% tomorrow. I'll give you a new dataset the day of the deadline. Take the last
day in that new data and predict the following day (i.e., you won't know if the stocks will go up or down; only I have that data).


Michel Ballings



Sign in to be able to add an answer or mark this question as resolved.