Skip to content

czarina-ds/Capstone-Proposal

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Capstone Project Proposals

Proposal 0

Using Fashion Product Dataset, I want to predict the category of the products by combining CNN modeling on the images with NLP analysis on product descriptions. I also think of timeseries forecasting given the season and year variables predicting price of the products. Lastly, implementing a recommender system based on the product's similarity.

The Data: A total of 44,446 products with multiple category labels, text descriptions, and images.

Proposal #1

Using Rent The Runway Dataset, I want to predict product rating using NLP on customer reviews, Time Series Forecasting given date rented/reviewed, and Classification or neural network algorithm on the remaining features (numerical and categorical). Possibly, create recommender system.

Rent The Runway allows people to rent clothes.

The Data:

  • Number of customers: 105,508
  • Number of products: 5,850
  • Number of transactions: 192,544

(Also found on Kaggle)

Proposal #2

Using Women's Intimate Apparel Dataset, I want to predict the price of product across different companies using NLP on product description, and Regression or neural network algorithm on the remaining features (numerical and categorical). Alternatively, classify products according to company.

Number of Products per Company:

  • Aerie: 24,488
  • Amazon: 26,251
  • B.tempt'd: 3,155
  • Calvin Klein: 4,276
  • Hanky Panky: 33,138
  • Macy's: 39,730
  • Nordstrom: 11,723
  • Topshop: 2,990
  • Victoria's Secret: 423,190

Total of 568,941 products

Proposal #3

Using Instacart Dataset, I want to recommend items to users for their next orders using clustering and market segmentation.

The dataset is anonymized and contains a sample of over 3 million grocery orders from more than 200,000 Instacart users. For each user, we provide between 4 and 100 of their orders, with the sequence of products purchased in each order. We also provide the week and hour of day the order was placed, and a relative measure of time between orders.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published