Scalarr
Viacheslav Panchenko has been working in the software development field since 2009. From 2009-2010, they worked as a PHP Developer at Gameloft, where they were responsible for WAP-site development and maintenance. From 2010-2011, they worked as a PHP Developer at CodeTiburon, where they were responsible for web development and maintenance. From 2011-2012, they worked as a Web Developer at WebDevs, where they were responsible for web development and maintenance. From 2012-2014, they worked as a Web Developer at Zfort Group, where they were responsible for web development and maintenance, and was responsible for estimating, planning and workload management. From 2014-2016, they worked as a Software Engineer and Team Lead at Oracle | TOA Technologies, where they were responsible for development, maintenance and refactoring of the ETA-direct product. From 2016-2019, they worked as a Full Stack Developer and Team Lead at Valor Software, where they were responsible for architecture design from scratch, workload allocations planning, new features development, maintenance and refactoring, teamwork and technical assistance, and code-review. Viacheslav worked with Angular 5, TypeScript, RxJS, HTML, Sass, Bootstrap, Node. js, Nestjs, TypeORM, MySQL, CI & CD, and Git. From 2019-2021, they worked as a Frontend Developer at Scalarr. Currently, they are working as a Frontend Developer at AI EdgeLabs.
Viacheslav Panchenko attended the National Technical University "Kharkiv Polytechnic Institute" from 2003 to 2009, where they earned a Bachelor's degree in Automated Systems Management.
This person is not in any offices
Scalarr
Scalarr is an innovative, Machine Learning based anti-fraud solution that detects the mobile app install fraud with dramatically improved accuracy. There are a lot of different types of app install ad fraud, although the traditional rules-based analysis used by existing solutions helps to detect only few of them. By applying to both unsupervised and semi-supervised machine learning algorithms, Scalarr solves the problem by analyzing deeply hundreds of features and variables, thus reducing efficiently the number of false positive and false-negative errors. With its unique self-learning engine it helps mobile advertisers to stay ahead of fraudsters without any need to update constantly the rules, as they modify their attack techniques.