Kazi Amit Hasan

Kazi Amit Hasan

PhD Student in School of Computing at Queen's University | Ex-ML Engineer at ACI Limited

Experience

Queen’s University

Graduate Teaching Assistant (January 2023 - Present)

Responsibilities:

  • Head Teaching assistant of CISC 235: Data Structure
  • Teaching assistant of CISC 320: Fundamentals of Software Development
  • Teaching assistant of CISC 351: Advanced Data Analytics

    • Louis W Bray Construction Limited (MITACS Business Strategy Internship)

    Data Scientist Intern (October 2023 - Present)

    I have been awarded the MITACS Business Strategy Internship (BSI) to work with Louis W Bray Construction Limited this fall. I will be collaborating with the Louis W Bray team on an engaging data science project, aiming to provide them with enhanced analysis and insights into industry data.

    ACI Limited

    Machine Learning Engineer (February, 2021 - July, 2022)

    Responsibilities:

  • [Analytics & AI] Developed a Social Media Analytics tool that can measure different perspectives of the audience towards a post which can improve a brand quality.
  • [Analytics & AI] Developed a customer segmentation system based on recency, frequency and monitory value features to help the business to focus on different segments of customers.
  • [Recommendation System] Developed a recommendation system for ACI retail business to push customers from one segment to another segment based on their purchased history.
  • [Analytics & AI] Created a baseline to identify of emerging doctors by analyzing and creating features of their FourP data to assist the field force to take the right steps based on the analytics.
  • [Analytics & AI] Developed a dashboard by analyzing the behavior patterns of different customers based on their credit history by using ML
  • [Analytics & AI] Developed a dashboard that provides deep insights about product performance based on different parameters. Enriched the project by using ML methods to provide forecast, predictability. We have used our own developed social media scrapper and analyzed their contents and other parameters using ML. This project automated the whole existing manual process.
  • [Analytics & AI] Created a sales tracking report which shows various insights from data. Business leaders can observe daily, weekly, monthly, yearly trend of sales. Also, they can monitor the sales against the target. We implemented the trend analysis using fb prophet.
  • Assisting Field Force to Take Right Steps from AI and BI Based Analysis
  • Assisting Businesses to Take Right Decision through Insights From Different Businesses Data
  • Generating insights using Power BI

    • Kaggle Expert (x4)

  • Competition Expert: ranked 844th out of 162,151
  • Notebooks Expert: ranked 262th out of 140,050
  • Discussion Expert: ranked 283th out of 162,435
  • Datasets Expert: ranked 124th out of 25,284

    • MyMedicalHUB

    Research Student (May 2020 - September 2020)

    Responsibilities:

  • Developed a machine learning model that analyzes the potential risk factors of Musculoskeletal Pain and find out interesting patterns among the symptoms.
  • Developed a facial expression, age, sex detection and recognition ystem that can detect features using a webcam.
  • Worked on developing a symptom checker.

    • Thesis

    Prediction of Clinical Risk Factors of Diabetes Using Multiple Machine Learning Techniques Resolving Class Imbalance

    Projects

    PR Stats

    • PR-stats is an open-source python library that brings different stats about pull requests.
    • Github: PR Stats
    • Pypi link: PR Stats

    data inspector

    • Data Inspector brings a total of 15 essential exploratory data analysis, data cleaning automations to make a dataset understandable. This is a perfect tool to get started with you data.
    • Github: data-inspector
    • Pypi link: data-inspector

    An Empirical Study on the Latency of Time to First Response In GitHub Pull Requests

    • This is a course project of CISC 834. More details are coming soon.
    • Language used: Python
    • Development Tools: Jupyter Notebook, PyCharm

    A Study on Privacy Preserving Machine Learning with Homomorphic Encryption

    • This is a course project of CISC 870. Machine learning is being used in sectors from different domains, it often needs to deal with data that are extremely confidential. When sensitive data is used to train a machine learning model, the model’s reliance on sensitive user data renders it unsuitable for creating Machine Learning workflows without compromising user privacy and confidentiality. These considerations apply to each and every machine learning method or model that deal with sensitive data. According to the findings of this project, we recommend the adoption of a customized homomorphic encryption scheme as a means of mitigating this danger. This scheme will enable proper encryption of user data by making use of a combination of public and private keys. In this project, I have explored different types of homomorphic encryption schemes. Also, I experimented the scheme in a sensitive dataset using linear regression. It has been noted that the encryption does a good job of preserving the confidentiality of the input test data as well as the data that corresponds to the results of the regression model. It protects the machine learning model and any sensitive user data that is linked with it from attacks involving model inversion as well as membership inference.

    • Github: (Link)
    • Language used: Python
    • Development Tools: Jupyter Notebook, PyCharm

    Risk Factors Analysis of Musculoskeletal Pain in Clinical Practice

    • In this project, I tried to analyze the risk factors of Musculoskeletal Pain and tried to find out some interesting patterns among the symptoms. Association Rule mining and Statistical Logistic Regression were used to get the insights and to find out the risks.
    • Github: (Link)
    • Detailed blog: (Link)
    • Language used: Python
    • Development Tools: Jupyter Notebook

    Implementations of Neural Network Algorithms

    • This repository contains the lab work of the course CSE 4204 (Sessional of Neural Networks and Fuzzy Systems). I have implemented Nearest Neighbor, Single Layer Perceptron Learning, Multi Layer Perceptron Learning, Kohonen Self-Organizing Neural Network annd Hopfield Neural Network algorithm.
    • Github: (Link)
    • Language used: Python
    • Development Tools: Jupyter Notebook

    Sentiments Analysis of Twitter Data

    • A project which fetches real-time data from Twitter using credentials and analyzes the sentiments and generates a visual that represents the sentiments of a specific word/tweets. Users can submit a word and sample numbers, the UI will show the sentiment visuals.
    • Github: (Link)
    • Language used: Python
    • Development Tools: Jupyter Notebook