Marcani is an online shopping marketplace which is powered by one of the biggest community of Japan where users can sell pretty much anything.The community wants to offer price suggestions to the sellers but is a tough task as the sellers are enabled to put just about anything, or any bundle of things, on mercani’s marketplace.
It can be hard to know how much something’s really worth. Small details can mean big differences in pricing. For example, one of these sweaters cost 335 dollars and the other cost 9.99 dollars. Can you guess which one’s which?
- The task of this case study is to build an algorithm that suggests the right product prices for shopping app from product name, user inputted text descriptions of the product, category name, brand name, item condition, and shipping information.
- The challenge was about creating a model that would help sellers to price their products.Pricing should be intermediate between sellers and buyers.
- The most challenging part was that this was a kernel-only competition, which meant the training and inference of the model would be in a container environment provided by Kaggle. The script had to finish within 60 minutes and consumed no more than 16 GB of RAM. The test dataset was also quite large so that it couldn’t be loaded into memory at once for inference, and batch inference was required.
- Machine learning is the fastest growing field in the world.
- Everyday there will be a launch of bunch of new algorithms. Some of them may work and some may not work on the data.
- Their is no such ML algorithm that gives the super result then all the existing models. If it exists then all the models will be gone into dustbin.
- Basing on the Prior Knowlege, domain excepts, from the problem statement and even from the first price winners one chooses the algorithm to tackle their problem.
- Let's try a bunch of regression models to apply on the dataset and we even try a ensemble MLP models on our data.
You can see my article on this here: https://medium.com/@chaitanyanarava/mercari-price-suggestion-challenge-66500ac1f88a