If you are participating in the Academia Datathon 2018, or just wanna be a crypto superhero forecasting cryptocurrency prices, this article was made just for you! It is a quick reference to tons of materials to get you started on the topic.
In this article, you will learn about the technology that makes these applications tick, and you will learn how to develop natural language processing software of your own.
Find out ALL sources of meat that have been used to produce a certain sausage and ALL organisms (or traces of them) that should not be found in the sausage (pathogens, bugs, even human).
ReceiptBank will provide an extensive dataset of invoices hidden inside PDF files, which you can uncover by developing an algorithm that detects how many documents are contained in each PDF file.
Telenor gives you a rare chance to do social network analysis on the best kind of data set for this – telecom data.
Do you know what KFC, Pizza Hut and Taco Bell share in common? The same parent company – ‘Yum! Brands’. Find out about this and other secret relationships in the business world by building an NLP algorithm that deduces the parent company from text.
Have you ever wondered if retailers actually make more money from price discounts? Or what is the impact of promotions in Amazon on the sales in Walmart? The SAP case is about price optimization and promotional effectiveness.
The key to every great model is clean data (“garbage in – garbage out”), and ZenCodeo challenges you to dive deeper into data preparation by creating unique IDs from all sorts of company names.
Identrics gives you an opportunity to build an NLP algorithm that extracts key words from news about companies.
VMware gives you a chance to organize better the support section of their website by grouping together articles dealing with the same problem.