The Academy of Continuing Education at Shiv Nadar University Delhi-NCR, in partnership with MachineHack, is launching an annual Analytics Olympiad, starting October 21, 2021 for data scientists and machine learning professionals. The winner of the competition will be recognized as the 2021 Analytics Olympiad and will be awarded a cash prize of INR 100,000.
The Championship has been primarily designed for data science enthusiasts, learners and professionals in India, to provide them the opportunity to showcase their skills, leadership potential in business analytics, and for them to advance in their careers.
Shiv Nadar University, Delhi-NCR, is an ‘Institution of Eminence’, as recognized by the Government of India – a coveted status it has received in pursuit of excellence as a multidisciplinary and research-focused university. The University’s Academy of Continuing Education aims to facilitate best-in-class knowledge, practices and skill development offerings to the growing ecosystem of lifetime learners and leaders, both within and outside the University. With distinguished academics as the University’s faculty members and program instructors, the Academy of Continuing Education offers uniquely crafted programs that are delivered in the most innovative ways, bringing together the very best of the University’s rich intellectual resources.
Through its unique certification program in data sciences and business analytics, the university aims to help students prepare for today and their future careers. The collaboration between the Academy of Continuing Education at Shiv Nadar University Delhi NCR and MachineHack hope to strengthen the data science community in India and pave the way for innovation in business analytics.
It is a first-of-its-kind opportunity for data science learners, enthusiasts and working professionals to showcase their talent and technical prowess. Take part in this exclusive challenge, and propel your career, along with some exciting cash prizes and other benefits.
Analytics Olympiad will be held in three phases:
- Phase #1: Solving the problem statement on MachineHack platform
- Phase #2: Presentation Round for the top 50 leaderboard contestants
- Phase #3: Jury evaluation round for the top 10 shortlisted contestants from the ‘Presentation Round’.
Problem Statement & Description
The sales in the mega marts are critical to making them sustainable. As a matter of fact, the rise of several marts has created buyers of different categories who are critical about the quality of products at the right price.
In Analytics Olympiad 2021, the data science & machine learning community has been challenged to build an ML model and predict the sales of each product from each outlet. The participants also need to use the model to analyse the properties of the product in the stores and find ways to increase sales.
Sklearn models support the predict() method to generate the predicted values.
You should submit a .csv file with exactly 37,656 rows with 1 column (sales).
Your submission will return an Invalid Score if you have extra columns or rows.
Note: Do not shuffle the sequence of the test series.
For participants using Pandas: submission_df.to_csv(‘my_submission_file.csv’, index=False)
- The submission will be assessed using the RMSLE metric. You can use np.sqrt(mean_squared_log_error(actual, predicted)) to calculate the same.
- This challenge supports both private and public leaderboards.
- The public leaderboard is evaluated on 30% of test data.
- The private leaderboard will be available at the end of the challenge, evaluated on 100% of test data.
- The final score represents the score achieved based on the best score on the public leaderboard.
First Prize: INR 1 Lakh
Second Prize: INR 30,000
Third Prize: INR 20,000
Note: TDS will be deducted as per the government norms.
The winner will be judged on the following criteria in the final jury round:
- 30% business outcome/impact
- 20% innovative + creativity
- 20% algorithm and ML approach
- 15% statistical analysis
- 15% presentation + communication
- Train.csv – 87,864 rows x 09 columns (includes ‘price’ columns as target)
- Test.csv – 37,656 rows x 09 columns
- Sample Submission.csv — Please check the “Evaluation” section on MachineHack Page for more details on generating a valid submission.
- Item identification number
- Item weight
- MRP of the product
- Outlet ID
- Outlet establishment year
- Size of the outlet
- Type of the outlet
- Total sales from the outlet
Application of Knowledge:
- Knowledge of RMSE computation.
- Knowledge of underfitting vs overfitting.
- Applying analytics tools to Big datasets.
October 21, 2021: Analytics Olympiad begins. The participants can start downloading the dataset, solving, and submitting their solutions on the MachineHack platform.
November 8, 2021: The leaderboard is frozen, with the top 50 leaderboard contestants to participate in Phase #2
November 9, 2021: Phase #2 will start where the top 50 participants from the leaderboard will need to share a presentation on their problem statement analysis, solution approach, business outcome, and real-world impact by November 12, 2021.
November 19, 2021: Final top 10 contestants will be decided. The winners of this round need to work on bench data released and prepare for the final jury round.
November 26, 2021: Phase #3 will start, where the final top 10 contestants will arrive at the Shiv Nadar University campus.
November 27, 2021: The final jury round will be conducted. The top three winners of this Analytics Olympiad will be awarded by Shiv Nadar University.
- If any of the details entered are found incorrect, Analytics India Magazine and Shiv Nadar University reserve the right to disqualify any participant.
- Any external dataset usage is strictly prohibited. The participants will be disqualified if found using any external dataset.
** NOTE: Academy of Continuing Education, Shiv Nadar University Delhi NCR and MachineHack reserve the right to modify and change any of the terms of the competition including the final round format based on the prevailing Covid situation.
- The participant must be a citizen of India.
- The participant should be above 18 years of age.
- The participant must hold a valid government ID, such as a PAN card or Aadhar Card.
- The participant needs to have a valid bank account based in India.
- If shortlisted for the final jury round, the participant should be in agreement with travelling to Shiv Nadar University, Delhi NCR.
Here is some of the important information regarding travel and accommodation to Shiv Nadar University:
- Shiv Nadar University will book a return flight ticket for the shortlisted contestant from the nearest metro city of their residence. Please note that meals during the flight journey will not be included in the ticket, and any expenses towards the same need to be borne by the travelling contestant.
- The shortlisted contestant will need to manage and bear travel expenses, logistics, airport transfers, etc., between their residence and the airport of the nearest metro city from where they need to embark or disembark their flight journey.
- Shiv Nadar University will only manage the airport transfers of the shortlisted contestant between their Noida Campus and the Indira Gandhi International Airport terminal at Delhi.
- Shiv Nadar University will not be responsible for the travel, accommodation, logistics, hospitality, etc., of any fellow co-passengers who would accompany the shortlisted contestant.
- It will provide food and accommodation to the shortlisted contestant on November 26 and November 27, 2021, only between the scheduled campus arrival and campus departure times, free of charge.
- Only the shortlisted contestants will be provided authorised entry and exit to the university campus, and only on the designated date and time as per the schedule of the championship.
- Communication and queries will not be entertained by Shiv Nadar University and are to be made only to the contact details provided on the MachineHack platform.
[Update] October 26 | 12:21 | Data Analytics Championship is now renamed as “Analytics Olympiad” and all the registered participants are automatically included in the hackathon.