Hi!
I'm Amir Masoud Sefidian

Data Scientist

W
elcome. I started programming as a C++ developer for AVR microcontrollers when I was 14. After four years of programming for high school’s robotics team, I was motivated to pursue the Computer Science field. I received my Bachelor’s degree in Computer Engineering in 2015. I was directly admitted to M.Sc. program as a talented student. I successfully completed my Master's degree in Computer Engineering in 2017 where I worked on Machine Learning and Data Mining algorithms especially focused on data preprocessing and missing values imputation techniques. Currently, I am a Data Scientist at ParticleB focusing on Algorithmic Trading and also Recommendation Systems. I’d love to combine my passion for learning with my software development skills to build intelligent products!

Skills & Experience



Programming Languages

Proficient in:
  • PYTHON:
    • Machine Learning
    • Data Science
    • Web
Familiar with:
  • C/C++
  • Java
  • PHP
  • WebDev Stack (HTML, JavaScript, CSS)

Databases

  • MySQL
  • MongoDB
  • Elasticserach
  • PostgereSQL
  • Redis
  • InfluxDB

Other Tools & Technologies

  • Git
  • LATEX typesetting language
  • Grafana
  • Raspberry Pi

Projects

  • 2021, As a member of ParticleB data team, designed and developed a recommendation system to help FIDIBO (Iran's biggest digital platform of Ebooks, Audiobooks, and Podcasts) users discover new and relevant items by providing personalized recommendations and similar items recommendations.
  • 2020, AI-based song's Vocal/Instrument separator web application.
  • 2020, 2D Landmark Detection & Robot Tracking (SLAM) using Graph SLAM algorithm.
  • 2020, 2D vehicle trajectory reconstruction from raw sensor data.
  • 2020, Developed an image captioning service on (MS COCO) dataset using PyTorch framework.
  • 2020, Disaster Response Multi-label Message Classification for Figure Eight dataset.
  • 2020, IBM Recommendation System.
  • 2020, Developed an hourly energy consumption prediction service for PJM Interconnection LLC Energy Consumption dataset based on GRU/LSTM networks using PyTorch framework.
  • 2020, Developed a Sentiment Analysis (Positive/Negative reviews) service for Amazon customer reviews dateset based on LSTM networks using PyTorch framework.
  • 2020, Developed a Facial Keypoint Detection system that takes in any image with faces, recognizes and detects faces, and predicts the location of 68 distinguishing keypoints on each face based on Deep CNNs (NaimishNet Architecture) using PyTorch framework.
  • 2019, Developed data analysis and machine learning microservices in order to analyze organizational time series data using Python, Redis, Apache Kafka, gRPC, Protobuff, and Docker.
  • 2019, Developed a real estate application using the Django & PostgreSQL.
  • 2018, Designed and implemented a web-based appointment scheduling, accounting, and management system for a consultation institute to efficiently manage their 30000+ appointments, 7000+ transactions, and 3000+ clients.
  • 2016, Designed and developed a novel missing data imputation framework using Self-Organizing Map (SOM) neural networks and Weighted K Nearest Neighbors technique using Python.
  • 2015, Designed and implemented a simple word segmentation algorithm for Persian text images using morphological operations in Matlab.
  • 2014, Developed first carpooling website in Iran (4paaye.ir) (Winner website of 8 th Iranian Web and Mobile Festival (IWMF)).

Teaching/Research/Professional Experience

  • Data Scientist, ParticleB.
  • Researcher, Computer Science R&D Laboratory, Faculty of Computer Engineering, Shahid Rajaee University.
  • Reviewer, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems (IJUFKS).
  • Reviewer, International Journal of Information Technology, and Decision Making (IJITDM).
  • Teaching Assistant , "Database" (Undergraduate), "Data Mining" and "Decision Support Systems" (Graduate), Faculty of Computer Engineering, Shahid Rajaee University, Instructor: Dr. Negin Daneshpour.

Contact Me

Write Your Message