Code: EDI-2019-8-JOT_1

Domain: Internet & Media


Massive classification of keyword lists.

Proposed by


JOT Internet Media is part of Cube Ventures, one of the leading digital groups in Europe. Based in Madrid and with offices in Germany, Mexico, Brazil and Italy and more than 280 employees, the group is focused on lead generation, services monetization, digital marketing, media and investments.


Currently, the set of variables used to describe the marketing campaign indicator only includes the level 1 Google category. Being possible of classifying any keyword up to the seventh level (the lowest) will enable the company to implement advance clustering and analytics procedures to improve the both the bidding strategy and the design of the related ads. In the market there are solutions trying to cover these issues, but they are limited both in languages, data volume capabilities and final classification accuracy.

Based on JOT’s data basis, it is required the massive classification of keyword lists. Marketing agencies and small companies used to implement marketing campaigns defined by 500 – 1000 different keywords. On contrary, due to the analytic approach and worldwide coverage, JOT’s keyword lists include millions of keywords, covering up to 17 different languages.

For that reasons, the solution solving this challenge has to deal with large number of keywords in different languages and the same time. Volume of data (keywords) and processing time will be considered as the key success features.



The challenge has the following sample datasets available for download

Expected outcomes

  • High accuracy classification (>95%) of millions of keywords covering 17 languages in all Google categorization levels
  • Automation of the keyword classification with an upper limit of 500 keywords per minute
  • As a final result, to have a minimum of 200 million of keywords completely categorized
  • Implementation of an agile API enabling the communication (upload/download) of large keyword list
  • Improve the performance of the campaigns by 10% based on the optimization of the ads thanks to the keyword categorization

How do we apply?

Follow by Email