As people who use feminine products and services regularly, it is hard not to notice the fact that there are more expensive prices levied on them. We wanted to examine this phenomenon of gender-based price discrimination by analyzing data pulled from the popular shopping website, Amazon.ca and compare products marketed towards women with other, generally cheaper contemporary products.
What it does
The user can input any Amazon link to a specific product into our webpage, which will then be run through APIs that analyze data from Amazon and compare the product against other similar results to determine if there is any pink tax leveraged upon it. We will also run the name of the product through the language-analysis toolkit of Co:here API to conduct sentiment analysis to determine if the type of keywords match the marketing strategies utilized for feminine products.
How we built it
The back-end was developed with Node.js libraries and APIs (Amazon Pricing and Product Info for specific product information and Real-Time Amazon Data for search results based on keywords).
The keywords were extracted from the generative model for entity extraction from Co:here and fed into the data-scraping API mentioned above for results. Furthermore, the classify functionality from Co:here was used to conduct sentiment analysis on the title of the specified product to determine whether it seemed to be marketed as a feminine product.
The front-end was developed with React.js and UX designs from Figma. Express.js was used as middleware to connect the front-end to back-end.
Challenges we ran into
Web scraping was a bit of a challenge with the security measures on different webpages according to Amazon policies. However, there were useful APIs that helped us extract the required data for our analysis. There was also trouble with resolving dependencies both within backend and conducting requests from front-end for analysis. We resolved this using Express.js as a simple, easy-to-use middleware.
Similarly, there was trouble getting front-end elements to talk when developing the UI design. Online resources were useful in resolving this issue.
Accomplishments that we're proud of
We're proud of dealing with large data sets extracted through the tedious process of web scraping and optimizing them to run in good running time. We are also excited to see the results of the generative model that we used to analyze our data from Co:here.
We're also proud of Ameya coming up with our cute mascot, Peach and our beautiful, responsive UI design. Our team worked really hard on this challenging project.
What we learned
We learnt to adapt and overcome challenges in difficult code quickly and resolve problems efficiently. The backend team learnt new technical skills in libraries like Node.js and Express.js and performing requests to the server. We also learnt more about responsive design through React.js and deploying the webkit to a domain.
What's next for just peachy
We would love to adapt the web app for more platforms like mobile and increase accessibility for the web page. We would also like to perform generative analysis on a bigger dataset to generate better results for a larger catalogue of products that users might want to check.
Log in or sign up for Devpost to join the conversation.