I am trying to work using Amazon machine learning, but the data set that I have is small. The model I want to build is for regression based predictions and the domain I am aiming for the data set to belong is financial, say product price prediction, price and demand prediction based on macro/micro economic factor.

I am looking for a data set that contains factors that lead to variations in value of a product or commodity. For example, I would like to predict the value of 1 unit of polyester yarn after 1 year. The factors which influence the yarn price are say - prices of crude oil, GDP of country,figures of IIP, inflation etc. So I would like a data set that contains the quotes of these factors on which the final price depends.

I find difficulty assembling this data myself because I don't know all the factors that contribute to a certain predictive price. Does anyone know of a dataset I can start with that sounds like it might contain these factors?


There are multiple datasets available in the internet but you need to pay for most of them. One of the best datasets for starting (and it is free) is the Quantquote Free dataset.

You can download it from here.

This is the description (borrowed from their website):

This collection of daily resolution data goes back to 1998 for all symbols currently active in the S&P500. It is updated quarterly, the last update was 07/31/2013.

  • $\begingroup$ i have made changes in my question , can you please have a re-look and suggest me data that belongs to the changes in question. i am sorry for the inconvenience. $\endgroup$ – Subham Tripathi May 9 '15 at 9:27
  • 1
    $\begingroup$ Given your new question, I suggest you to split it in two different questions: one asking for help on the predicition variables and the other asking for the dataset. $\endgroup$ – phyrox May 10 '15 at 7:39

Housing prices is a popular regression data set. Here is one example.

Car prices is an other popular choice. Here is one example.

Remember there is "no free lunch" in machine learning. Models tend to not generalize across domains.


Go to UCL Machine Learning Repository. You will find the various data sets by algorithms.

For example: Regression, Classification, Clustering etc.

I assure you that this will be really helpful for practicing algorithms.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.