
Emply.ru is looking for an investor

A week ago, our investor said that for a number of reasons, his income was reduced and he can no longer finance us in full. C August, the team will have to be reduced. To continue development and promotion, we are looking for additional investments.
During our work, we made two independent online projects, each of which has no analogues in our market:
They are unique thanks to the application of our technology for extracting facts from vacancies and resumes. Both services differ from existing solutions on the market in that they allow you to operate not with full-text search categories (the text contains “programmer” or “developer by” or “developer”), but with domain categories (programmer’s vacancy).
This approach allowed us to implement resume scoring - an assessment of the compliance of a resume with the vacancy parameters. This service for the employer or recruitment agency allows you to save the time of recruiters at the stage of the initial selection of resumes.
The user is required to set the vacancy parameters (mandatory requirements and evaluation parameters for which scoring will be conducted) and choose which resumes to analyze. Resumes for analysis can be downloaded independently (to protect personal data, we created an anonymizer program that leaves contacts on the employer's machine, and downloads anonymous resumes on emply.ru) or analyze the resume from our database, which is replenished with spiders (there were just 141 636 summary). As a result, the user sees a list of the most suitable candidates for the vacancy. For each indicated conformity assessment (in percent).
To analyze the texts, we created a system that we modestly call the "parser". The parser allows you to analyze the texts of vacancies and resumes and not just break them into blocks, like other resume parsers do, but extract facts from them (positions, skills, industries, etc.)
For this to work, we created a knowledge base of the subject area containing reference books of these very facts, their possible names (how this object can be called in a resume / vacancy), links and hierarchies of objects, and about a hundred thousand hand-crafted texts of vacancies and resumes on which our ML algorithms are trained.
All this wealth is documented, covered in tests, CI mechanisms, automatic deployment are adjusted. And even the team until August all in place.
We have preliminary agreements on the use of scoring with many companies, and we are negotiating integration with the largest Russian ATS (Applicant Tracking System) and job sites.
We welcome any suggestions!