Silver Sponsors

Bronze Sponsor

Welcome to Learn ML 2021 Grand AI Challenge!

The year 2020 has been an outlier year for finance analysts. Most of the past models have failed to give out great results on the 2020 financial data creating a need for more robust models to handle such outliers. Hence with this challenge, we wish to test your analytical modelling skills not for 1 stock but 5 to see if you have what it takes to create a model that can give predictions for the outlier 2020 year. All the best for the challenge!

The aim of this challenge is to predict the closing prices of 5 stocks using the given data.

The dataset consists of 3 files:

1. new_train.csv (for training)
2. new_test.csv (for test)
3. new_sample_submission.csv (for sample submission format)

This data should be used to train the model, no additional data is allowed to be used for the training process.

A "new_sample_submission.csv" is also provided for ease of the participants. To know the exact submission format, please check out "Submission Guidelines".

NOTE: The format of the submission csv must have the same date format as provided. The submission may show error if you manually put the values, hence, please copy the date attribute from "new_test.csv" to avoid such errors.

Platform partner

The score is displayed in reverse order of Root Mean Square Error (RMSE). "new_train.csv" file contains the data required for training.

The output of the model should be "output.csv" containing the following columns in this exact order for predictions on new_test.csv:

• Date   (Keep these same as given in new_test.csv, or your submission may be invalid)
• Close-Stock-1   (Closing price for Stock-1)
• Close-Stock-2   (Closing price for Stock-2)
• Close-Stock-3   (Closing price for Stock-3)
• Close-Stock-4   (Closing price for Stock-4)
• Close-Stock-5 (Closing price for Stock-5)

A "new_sample_submission.csv" is also given for reference which already contains the correct format required for submission.

...

Data Structure

new_train.csv consists of 36 attributes:

• Date  
• Open-Stock-1   
• High-Stock-1   
• Low-Stock-1   
• Close-Stock-1 (Part of Prediction)   
• VWAP-Stock-1   
• Volume-Stock-1   
• Turnover-Stock-1   
• Open-Stock-2   
• High-Stock-2   
• Low-Stock-2   
• Close-Stock-2   (Part of Prediction)
• VWAP-Stock-2   
• Volume-Stock-2   
• Turnover-Stock-2   
• Open-Stock-3  
• High-Stock-3   
• Low-Stock-3   
• Close-Stock-3   (Part of Prediction)
• VWAP-Stock-3   
• Volume-Stock-3   
• Turnover-Stock-3   
• Open-Stock-4   
• High-Stock-4   
• Low-Stock-4   
• Close-Stock-4   (Part of Prediction)
• VWAP-Stock-4   
• Volume-Stock-4   
• Turnover-Stock-4   
• Open-Stock-5   
• High-Stock-5   
• Low-Stock-5   
• Close-Stock-5   (Part of Prediction)
• VWAP-Stock-5   
• Volume-Stock-5   
• Turnover-Stock-5

How to make a submission?

1. Click on "My Submission"
2. On the next page, click on "+ New Submission"
3. Upload your CSV in the next page and click on "Submit for Review"

Please note:

1. You must submit your CSV file by uploading the CSV in the "My Submissions" section of this challenge.
2. Your submission will be auto graded and you will be able to see your results instantly.
3. If there is any error in the submission, your final score will be marked as 0 or invalid..

Judgement

1. Root Mean Squared Error (RMSE) will be used for evaluation
2. If the scores are tied, the person reaching the score FIRST will get the better rank.

Rules

1. We are using automatic anti-cheat system. Our system flags submission which have low trust scores. Manually modifying your submission CSV (via comparison of any form etc.), using image comparison techniques (pixel matching, file size matching etc,), in any form, can lead to your disqualification without any notice.
2. The participants must use only the provided dataset for training.
3. The submission should be in a proper format as described by "Submission Guidelines".
4. Late submission will not be accepted beyond provided deadline (Indian Standard Time).

NOTE: We may request for the code files if there is any discrepancy in your score. Your score will be marked invalid or you can be disqualified if the request for code is not fulfilled by you.