Qikai Alex G.

data scientist / machine learning engineer

Peut se déplacer à Paris

  • 48.8546
  • 2.3477
Proposer un projet La mission ne démarrera que si vous acceptez le devis de Qikai Alex.
Proposer un projet La mission ne démarrera que si vous acceptez le devis de Qikai Alex.

Localisation et déplacement

Paris, France
Peut travailler dans vos locaux à
  • Paris et 50km autour




Github : qikaigu qikaigu
  • 24 Repos
  • 0 Gists


Kaggle : Qikai Qikai
  • Expert Tier
  • 4627 Rang
  • 2 Bronze
  • 0 Argent
  • 0 Or

Stack Overflow

Stack Overflow : Qikai Qikai
  • 26 Réputation
  • 6 Bronze
  • 0 Argent
  • 0 Or



Compétences (18)

  • Langages
  • Débutant Intermédiaire Confirmé
  • Débutant Intermédiaire Confirmé
  • Cloud
  • Débutant Intermédiaire Confirmé

Qikai Alex en quelques mots

6+ years of experience in building end-to-end machine learning applications, solid fundamentals of data structures and algorithms. Cross-functional: be able to exchange with data analysts, data engineers, backend engineers and product teams.

I can help you build a scalable end-to-end machine learning applications on AWS. Leave me a message if you are looking for long term collaboration or want to rapidly prototype an MVP during a weekend.


M6 Digital Distribution - Groupe M6

Cinéma & audiovisuel

Data Scientist

Paris, France

novembre 2018 - Aujourd'hui

Automated Machine Learning Platform
• Build a general-purpose automated Machine Learning platform based on Apache Spark framework.
• Build a cross-platform (desktop, mobile and TV) lookalike audience extension system on top of the general-purpose ML platform, which extends the audience reach up to 6 times larger than the base audience.
• Build a video recommender system on top of the general-purpose ML platform serving millions of users.

A little Market - Etsy France


Data Scientist

Paris, France

mars 2014 - septembre 2017

Search Ranking
• Created the first Machine Learning powered application for millions of unique items on alittlemarket.com.
• Designed and developed a user behavioral data collecting system with Node.js and Elasticsearch.
• Developed a unique item purchase predictive model in Python(scikit-learn) and an Algolia reranking process.
• Deployed the predictive model in production as API using Flask.
• Designed and monitored Key Performance Indicators in Google Analytics and internal tools.
• Increased revenue by 15% (A/B test).

Recommender System
• Implemented a content-based recommender system with Spark Scala for millions of unique items.
• Parallelized batch jobs by using MapReduce programming model.
• Reduced job duration by optimizing algorithm's time complexity.

Autocomplete Suggestions
• Built a pipeline in Python for extraction and spelling correction of e-commerce expressions in French.
• Built a parallelization tool to reduce processing time with Python multiprocessing.

Recommandations externes