Cover image for MLWARE 2 - Recommendation Challenge
Login/ Signup

About MLWARE 2 - Recommendation Challenge

The last decade has seen a vast increase in the quantity of data, and proper analysis and informed prediction has become a challenging task. The subsequent increase in computational powers presented a solution, giving rise to a field of study called Machine Learning wherein computers learn to do stuff without being explicitly programmed. From driverless cars to personalized recommendations, facial recognition to automated speech assistance, Machine Learning is everywhere right now.

Recognizing this, Technex'17, the annual techno-management fest of IIT (BHU) Varanasi, and Samsung R&D Institute Bangalore present MLWARE - the perfect platform to design innovative and intelligent models, which can study the intricacies of data themselves to solve real-life problems. This competitive forum will also help the budding Data Scientists or Machine Learning engineers and researchers alike to assess their potential, and grow both in confidence and ability.

MLWARE 2 is one of the two contests held under MLWARE and is a 60 hour hackathon which allows participants to explore Machine learning applied to Recommendation based systems - perhaps, the most prevalent application of Machine learning online today.

Rules

Contest Guidelines

  • One person cannot participate with more than one user accounts
  • External data sets and sources cannot be used in the modeling exercise
  • Appropriate taxes will be applicable on the prize money
  • Winners will be required to upload the description of the approach along with the source code has to be uploaded in addition to the predictions on the test dataset. The approach and insights matter as much as the result in real world analytics! This will also help us ensure that no plagiarism takes place
  • Winners will be required to make a presentation (over skype) to explain the algorithm and methodology of solving this problem

Tools

  • You are free to use any tool and machine you have rightful access to
  • You can use any programming language or statistical software

Submission

  • Submission file must be a zip file containing two CSV files "Replenishment.csv" and "Withdrawal.csv". These file names are case sensitive also.
  • Column Name must be similar as it is in the "Withdrawal.csv" and "Replenishment.csv" and names of these columns are also case sensitive
  • Withdrawal.csv: (ID, ATM_ID, DATE, WITHDRAWAL) Replenishment.csv: (ATM_ID, Replenishment frequency, Replenishment amount)
  • There must be no missing value(s) in both submission files Replenishment frequency must be a whole number (0, 1, 2, 3, 4, 5 or 6 only)
  • You can use any programming language or statistical software

Solution Checker

  • You are free to use solution checker as many times as you want
  • Adding comment is mandatory for use of solution checker
  • Comments will help you to refer to a particular solution at a later point in time

Final Submissions

  • Setting final submission is mandatory. If you don't make final submission, your entry would be dis-qualified
  • No submissions would be entertained after the hackathon ends
  • Code file is mandatory while setting final submission. For GUI-based tools, upload zip file of snapshots of steps taken by you, else upload code file
  • The code file uploaded should be pertaining to your final submission. If we find any discrepancy between the two, your entry would be dis-qualified

Team formation

  • Maximum of 2 people can form a team
  • In case a team wins, prize would be distributed equally among team members
  • Team once created can't be dissolved
  • Teams can't be merged

Expected conduct

  • At any point in the hackathon, you are expected to respect fellow hackers and act with high integrity
  • Slack Live Chat admins hold the right to blacklist/block any participant found to use foul/disrespectful language. Chat forum will be closely monitored
  • Analytics Vidhya holds the right to disqualify any participant at any stage of competition if found indulged in fraudulent practices

Registration Fee

Free
DataHack Summit