András Kárpáti, Developer in Budapest, Hungary
András is available for hire
Hire András

András Kárpáti

Verified Expert  in Engineering

Data Scientist and Developer

Budapest, Hungary

Toptal member since April 29, 2022

Expertise
AlgorithmsMachine LearningArtificial IntelligencePythonSQLETLNumPyData EngineeringData ScienceX (Formerly Twitter) Development
Bio

András is a mathematician and economist by training, a data scientist by choice. With industry experience in telecommunications, logistics, finance, and retail, András excels at cracking tough statistical problems and building software solutions that last. Beyond his industry expertise, András teaches network science and machine learning to graduate students.

Portfolio

Prediction Machine
Python, X (formerly Twitter) API, Machine Learning, Pandas, Network Science...
TNX Limited
Scikit-learn, Machine Learning, Data Science, Data Engineering, Forecasting...
Lynx Analytics
Python, LynxKite, NetworkX, Machine Learning, Project Management...

Experience

  • Network Science - 6 years
  • Algorithms - 6 years
  • Python - 6 years
  • Machine Learning - 5 years
  • Scikit-learn - 5 years
  • Pandas - 4 years
  • Data Science - 4 years
  • PySpark - 2 years

Availability

Part-time

Preferred Environment

PyCharm, PySpark, Pandas, Scikit-learn, Seaborn, Matplotlib, Apache Kafka, Pytest, NumPy

The most amazing...

...product I've worked on was a general-purpose targeting software for telco companies, utilizing the property and strength of weak ties among social networks.

Work Experience

Senior Data Scientist

2021 - 2022
Prediction Machine
  • Created a model that predicts the stock market based on tweets.
  • Picked out the best authors to follow on Twitter using network science.
  • Handled the MLOps part of the project with analytics and metric tracking using DVC.
Technologies: Python, X (formerly Twitter) API, Machine Learning, Pandas, Network Science, Algorithms, Statistics, ETL, Machine Learning Operations (MLOps), Supervised Machine Learning, Artificial Intelligence (AI), Quantitative Finance

Senior Data Scientist

2020 - 2021
TNX Limited
  • Developed a pricing model that forecasted procurement prices for road freight.
  • Maintained several data pipelines to merge client historical data from Excel and APIs.
  • Oversaw client onboarding related to understanding their business and developing models.
  • Developed a response-time model that predicted individual responses by carriers.
Technologies: Scikit-learn, Machine Learning, Data Science, Data Engineering, Forecasting, Artificial Intelligence (AI), Python, SQL, Pandas, Network Science, Algorithms, Statistics, ETL, Machine Learning Operations (MLOps), Supervised Machine Learning

Senior Data Scientist

2018 - 2020
Lynx Analytics
  • Created a general-purpose, graph-based campaign-targeting model for telco companies that utilized the strength of weak ties property of social networks.
  • Developed a sales forecasting tool for mobile handset sales.
  • Created an assortment of optimization tools for fashion retailers.
Technologies: Python, LynxKite, NetworkX, Machine Learning, Project Management, Artificial Intelligence (AI), Network Science, SQL, Pandas, Algorithms, Statistics, ETL, Machine Learning Operations (MLOps), Supervised Machine Learning, Lynx

Data Scientist

2017 - 2017
EPAM Systems
  • Developed a prototype for automatizing reports from Excel to a web framework in Flask.
  • Used BI tools to deliver standardized reports for clients.
  • Took international business trips to meet with clients abroad.
Technologies: Python, Flask, Business Intelligence (BI), Machine Learning, SQL, Pandas, Statistics, ETL, Machine Learning Operations (MLOps), Supervised Machine Learning, Artificial Intelligence (AI)

Experience

OmniPurpose Targeting Engine

A LynxKite and PySpark-based targeting engine, utilizing the callgraph for a telco company. I created a targeting engine that works for any product by using the callgraph instead of traditional machine learning methods.

Assortment Optimization

An end-to-end solution that optimized the assortment for a chain of stores in Asia for a huge fashion brand. I created the solution by using Markov Chain Monte Carlo (MCMC) optimization, clustering, network backbone extraction, and other methods to arrive at the conclusion.

Education

2014 - 2016

Master's Degree in Applied Mathematics

Central European University - Budapest, Hungary

2011 - 2014

Bachelor's Degree in International Business

Corvinus University of Budapest - Budapest, Hungary

Skills

Libraries/APIs

Pandas, Matplotlib, NumPy, NetworkX, PySpark, Scikit-learn, X (formerly Twitter) API

Tools

Seaborn, PyCharm, Pytest

Languages

Python, SQL, Lynx

Paradigms

ETL, Business Intelligence (BI)

Frameworks

Flask

Platforms

Apache Kafka, LynxKite

Industry Expertise

Project Management

Other

Network Science, Algorithms, Economics, Machine Learning, Data Science, Data Engineering, Forecasting, Statistics, Supervised Machine Learning, Artificial Intelligence (AI), Probability Theory, Econometrics, Logistics, Microeconomics, Macroeconomics, Data Visualization, Optimization, Machine Learning Operations (MLOps), Quantitative Finance

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring