Hackathons are the best way of learning
Hackathons are fun, they are full of learning, intense competition and a lot packed in a matter of few days. You get to apply your learning on real life datasets and also compare yourself against the top data scientists from across the globe. Analytics Vidhya has now conducted Hundreds of hackathons and we would like to thank our community for the success they have seen. Your active participation and constant support have always motivated us to bring to you the best hackathons and practice problems from leading organizations around the world.
The only downside of a hackathon – they are short duration. If you have something coming up over the same weekend as the hackathon – you lose being part of the fun. That’s why one of the most common request from our users was to open up past hackathons for practice. If you wished for this yourself – wait no more. There is a big HUGE announcement coming up!
Announcement
We frequently get requests from our participants and users for access to datasets of closed hackathons. It gives me immense pleasure to announce that we will be opening most of the past hackathons for community practice. To start with, we are opening 5 hackathons as practice problems for all our users. We will open up more in coming days.
The new hackathons will essentially be clones of the original hackathons with the replica of the following databases maintained:
Leaderboard: This is a new development as for these contests, the leaderboard would not be blank on launch but would be populated by the leaderboard from the original contest. Participants would be able to try training that model which they did not get the time to do during the contest and check whether it actually beats No 1 😉
Submissions: Anyone can freely participate in these contests. However, those who participated in the original contest would also be able to access the old submissions that they had made during the original contest.
What does it mean for you?
More Discussions! More Collaboration! More learning!: Original contests might have had constraints w.r.t. sharing and discussing approach or solutions. However, now all the solutions and approaches would be discussed openly by all participants. Users can use the facility of sharing approach, code on leaderboard and also use the discussion forum to collaborate on using various techniques to learn and compete.
Team Participation: Participants can form a team of 2 to attempt the problems in tandem and learn from each other’s mistakes or just build a wonderful ensemble model to beat that top score
It means DataHack is going to be lot more fun, lot more engagement and you don’t need to wait for the weekends to keep your learning going. You learn
New Practice Problems
5 exciting challenges awaiting you at the DataHack! Read on.
Practice Problem: Food Demand Forecasting Challenge
Demand forecasting is a key component to every growing online business. Without proper demand forecasting processes in place, it can be nearly impossible to have the right amount of stock on hand at any given time. A food delivery service has to deal with a lot of perishable raw materials which makes it all the more important for such a company to accurately forecast daily and weekly demand.
Too much inventory in the warehouse means more risk of wastage, and not enough could lead to out-of-stocks — and push customers to seek solutions from your competitors. In this challenge, get a taste of demand forecasting challenge using a real dataset.
Practice Problem: HR Analytics Challenge
HR analytics is revolutionising the way human resources departments operate, leading to higher efficiency and better results overall. Human resources has been using analytics for years. However, the collection, processing and analysis of data has been largely manual, and given the nature of human resources dynamics and HR KPIs, the approach has been constraining HR. Therefore, it is surprising that HR departments woke up to the utility of machine learning so late in the game. Here is an opportunity to try predictive analytics in identifying the employees most likely to get promoted.
Practice Problem: Face Counting Challenge
The method of face detection in pictures is complicated because of variability present across human faces such as pose, expression, position and orientation, skin colour, the presence of glasses or facial hair, differences in camera gain, lighting conditions, and image resolution.
Object detection is one of the computer technologies, which connected to the image processing and computer vision and it interacts with detecting instances of an object such as human faces, building, tree, car, etc. The primary aim of face detection algorithms is to determine whether there is any face in an image or not. We challenge all the hackers to participate in this computer vision challenge that aims to test skills in deep learning and object detection.
Practice Problem: Identify the Sentiments
Sentiment analysis is contextual mining of text which identifies and extracts subjective information in source material, and helping a business to understand the social sentiment of their brand, product or service while monitoring online conversations. Brands can use this data to measure the success of their products in an objective manner. In this challenge, you are provided with tweet data to predict sentiment on electronic products of netizens.
Practice Problem: Predict Number of Upvotes
Crowdsourced online content platforms have a constant need to identify the best content in time to appropriately promote and thereby improve the engagement at the website. This challenge involves a similar problem of predicting the upvote count for a queries posted and identify the parameters that affect it the most.
End Notes
I am personally very excited about this announcement and I am sure our community will love this.
More datasets, more learning, more solutions from experts => a tone of learning and fun! Do let us know how you feel about this and which problems would you attack first!
IIT Bombay Graduate with a Masters and Bachelors in Electrical Engineering. I have previously worked as a lead decision scientist for Indian National Congress deploying statistical models (Segmentation, K-Nearest Neighbours) to help party leadership/Team make data-driven decisions. My interest lies in putting data in heart of business for data-driven decision making.
