Scroll To View More
Peter Hussami

Peter Hussami

Budapest, Hungary
Member since March 15, 2017
Peter is an expert in algorithms & statistics/data science, but his specialty—which few others can deliver on—is mathematical modeling. These tasks are often specified in human language at the start and he’s good at formalizing these problems and then delivering full, working solutions and integrating them (domain expertise in audio analysis/pattern recognition, identity verification, NPL, sensor analysis, scheduling, routing, & credit scoring).
Peter is now available for hire
Portfolio
  • UangTeman
    Python, Amazon AWS, Linux
  • Furukawa Electric
    Audio Analysis, Fast Fourier Transform Algorithm (FFT), Filters, Python
  • General Electric
    Audio Analysis, Fast Fourier Transform Algorithm (FFT), Filters, Python (NumPy)
Experience
  • Algorithms, 20 years
  • Statistics, 16 years
  • Statistical Modeling, 16 years
  • Machine Learning, 15 years
  • Artificial Intelligence (AI), 15 years
  • Data Science, 10 years
  • Python, 7 years
  • Big Data, 4 years
Budapest, Hungary
Availability
Part-time
Preferred Environment
Linux, Python
The most amazing...
...project I’ve ever worked on was a cool content-based music recognition system, back when nobody else had such a system.
Employment
  • Principal Data Scientist
    2015 - PRESENT
    UangTeman
    • Created and maintaining various statistical models for a lending company—the aim was to automate all aspects of the company's lending operations.
    • Designed and implemented several successful credit risk evaluation models. Notably, I built models that supported big data—they made inferences on heterogeneous records.
    • Designed and implemented statistical identity verification tools (big data style).
    • Built scrapers for various social networks.
    • Developed an OCR-based identity verification module.
    • Made various further prediction models for collection, residence verification, and more.
    Technologies: Python, Amazon AWS, Linux
  • Research Contractor
    2015 - 2017
    Furukawa Electric
    • Built a pilot system for direction detection using sound; specifically in an outdoor setting. The system's intended use is to enhance existing radar technology in the automotive field. Accuracy is lower than that of radar, but audio is a low-cost means to an orthogonal measurement.
    • Developed a solution was able to measure the direction of passing cars, as well as show a consistent direction for the car it was mounted on.
    • Ideated also physical solutions for alleviating wind distortion.
    Technologies: Audio Analysis, Fast Fourier Transform Algorithm (FFT), Filters, Python
  • Researcher
    2015 - 2017
    General Electric
    • Delivered a high-accuracy direction-detection system using sound only.
    • Fused the sound and video sensor data for enhanced motion detection.
    • Built a successful traffic counting and classification system that was able to count passing vehicles and separate buses, cars, and more.
    • Used Python (NumPy) to build the systems.
    Technologies: Audio Analysis, Fast Fourier Transform Algorithm (FFT), Filters, Python (NumPy)
  • Algorithm Developer
    2015 - 2015
    Analogy.co
    • Built natural language models (NLP) for semantic data analysis.
    • Developed automated semantic tagger modules for deriving meaning in the text.
    • Used various algorithm optimization techniques for asymptotic speedup of the semantic search.
    Technologies: NLP, Python
  • Algorithm Developer and Programmer
    2011 - 2015
    Applied Logic Laboratory
    • Built a syntax parser specifically for searching through English-language patents.
    • Developed an information-rich semantic representation over the parsed syntax.
    • Created a search engine for matching semantic information.
    • Built scrapers and built scraped data into a structured dictionary automatically.
    Technologies: NLP, C, C++, Python, Java
  • Research Intern
    2006 - 2006
    SAP
    • Created a server-side log analyzer. The log analyzer's purpose was to predict the identity based on user input.
    • Designed the log analyzer so that it parsed server logs into structured data and estimated their distance—delivering probabilistic results.
    Technologies: C, C++
  • Algorithm Developer and Programmer
    2004 - 2005
    Bioscrypt Corporation
    • Participated in building the company's fingerprint recognition algorithm. The algorithmic work included image cleansing, filtering, and feature extraction.
    • Wrote parts of the matching algorithm.
    • Developed exported APIs to the system.
    • Created test tools.
    Technologies: C, C++, Embedded C
  • Programmer | Inventor
    2000 - 2002
    Connexus Corporation
    • Invented one of the world's first content-based music recognition systems, it came earlier than the current market leader. The system monitored a large number of radio stations (US), to deliver high-accuracy recognition information of the contents, songs, commercials, recorded interviews etc.
    • Designed the system so that it made heavy use of the Fourier transform to convert audio data into a musical score.
    • Wrote fast algorithms that were supplied to match a time sequence of these fingerprints.
    • Built automated management tools for recording and tagging unknown patterns; inserting them into the central database and various other smaller components.
    Technologies: Audio Analysis, C, C++
  • Research Intern
    1998 - 1998
    IBM
    • Built a pilot program for converting an audio signal into musical notation. The criterion was for the musical score thus derived can be used for regenerating the original signal in a way that humans would still recognize it.
    Technologies: Audio Analysis (FFT), C, C++
Experience
  • Hungarian Spell Checker (Development)

    This is a rule-based syntax parser and spell checker for Hungarian. The purpose is to determine if a compound term is spelled as a single word, separated by a hyphen, or composed of multiple words.

  • How to Approach Machine Learning Problems (Publication)
    How do you approach machine learning problems? Are neural networks the answer to nearly every challenge you may encounter? In this article, Toptal Freelance Python Developer Peter Hussami explains the basic approach to machine learning problems and points out where neural may fall short.
Skills
  • Languages
    Python 2, Python 3, SQL, Python, C++, C, Java, R
  • Frameworks
    Machine Learning, Flask, Django
  • Paradigms
    Data Science
  • Storage
    MySQL, PostgreSQL
  • Other
    Statistics, Statistical Modeling, Statistical Analysis, Big Data, Data Structures, Algorithms, Artificial Intelligence (AI), Natural Language Processing (NLP), Numerical Methods, Mathematics
  • Platforms
    Linux
  • Tools
    Nginx
Education
  • PhD degree in Mathematics
    2005 - 2011
    Central European University - Budapest, Hungary
  • Bachelor of Science degree in Mathematics
    1995 - 2000
    Massachusetts Institute of Technology | MIT - Cambridge MA, USA
I really like this profile
Share it with others