About me

I am a Junior Data Scientist with a strong foundation in data science, machine learning, and deep learning. My passion lies in transforming data into actionable insights, and I have honed skills in Python, SQL, R, and advanced data visualization tools. With experience in data-driven decision-making projects, I am adept at using statistical analysis and machine learning models to derive meaningful outcomes. I am eager to apply my analytical expertise and problem-solving abilities to drive impactful solutions as a Data Scientist, Data Analyst, or Machine Learning developer.

Interests

  • Machine Learning

  • Deep Learning

  • Computer Vision

  • Medical Imaging

  • Large Language Models

  • Ai Agents

  • Graph Neural Networks

  • Human-Computer Interaction

Resume

Education

  1. University of Milan (UniMi)

    2025 — Present

    M.Sc in Data Science for Economics and Health

  2. University of Guilan

    2019 — 2024

    B.Sc in Computer Engineering
    CGPA: 3.69/4

Work Experience

  1. Apprenticeship at Infinite Modern Technology

    Jul 2024 - Present

    • I have learned data processing techniques and tools. Additionally, I have gained knowledge in machine learning concepts and working with algorithms. Furthermore, I have undertaken several data science projects as part of this learning journey.

  2. Research Assistant at Guilan University

    Nov 2023 - Present

    I lead a research initiative supervised by my professor, focusing on various medical images.

Teaching Experience

  1. Artificial Intelligence

    Fall 2022

    University of Guilan
    Instructor: Dr. Y. Boreshban
    Head TA

  2. Algorithm Design

    Spring 2023

    University of Guilan
    Instructor: Dr. A. Khozaei
    Head TA

  3. Software Testing

    Spring 2023

    University of Guilan
    Instructor: Dr. F. Feyzi
    Head TA

Projects

Selected Projects

  1. Transaction Fraud Detection Using GNNs and Tabular Models

    Developed a comprehensive fraud detection system using supervised (Tabular Transformers, Neural Networks) and semi-supervised (Graph Attention Networks, GraphSAGE) learning models. Conducted EDA, feature engineering, and implemented a hybrid loss for graph-based models with 15% labeled data, achieving competitive performance. Utilized Python, PyTorch, and data visualization to analyze imbalanced transaction datasets effectively.

  2. FraudRide-Analytics

    It’s a data analytics project focused on detecting fraudulent bikers in ride-sharing services. It leverages statistical analysis and anomaly detection techniques to identify suspicious patterns in ride data, preventing fraud and ensuring fair platform usage.

  3. Essay Agent

    Essay Agent is an intelligent assistant for writing essays, built with LangGraph and Streamlit. It guides you through the full cycle of essay creation: planning, researching, drafting, and critiquing.

  4. Anatomy of a Blockbuster

    This project investigates what factors contribute to a movie becoming a blockbuster. Using the Kaggle Movies Dataset, we analyze how genre, budget, runtime, release date, cast & crew, and production companies influence box office revenue and audience reception.

  5. PotholeSegmentation

    This project focuses on the development and application of an advanced deep learning model, specifically YOLOv9, for the detection and segmentation of potholes in both images and video streams. Leveraging a custom dataset, the model has been fine-tuned to achieve high precision and recall rates through the use of optimized hyperparameters, data augmentation techniques, and advanced training strategies such as mixed precision training and gradient accumulation. Key achievements include a mAP50 of 0.807 and a Mask mAP50 of 0.825, underscoring its effectiveness in practical applications.

  6. Amazon Reviews

    A machine learning model was created and trained on Amazon Reviews to perform sentiment analysis. The dataset underwent comprehensive preprocessing steps, including tokenization, removal of stopwords, lemmatization, stemming, elimination of tags and emojis, and normalization. Logistic Regression was utilized for the sentiment analysis task on Amazon Reviews. The repository includes resources and code for implementing various sentiment classification models, such as Embedding Models, BERT, and Simple Neural Networks.

  7. AlzMRI-Net

    The AlzMRI-Net project develops a deep learning model to classify MRI scans into four stages of Alzheimer's disease: MildDemented, ModerateDemented, NonDemented, and VeryMildDemented. Leveraging transfer learning with a pre-trained EfficientNet-V2-L model, this work fine-tunes the model on a specialized dataset using PyTorch. Advanced techniques such as mixed precision training and gradient accumulation are employed to enhance performance and efficiency. The model achieves a test accuracy of 99.19%, with comprehensive evaluation metrics, including precision, recall, and AUC, underscoring its effectiveness in Alzheimer's disease classification.

  8. Paper Summarizer

    The goal of this project is to simplify the process of reviewing the latest research papers by providing concise summaries generated using BART, a state-of-the-art large language model (LLM). The tool fetches the most recent papers from PubMed and arXiv based on a user-defined query and presents them through an interactive interface. Users can easily select papers and view detailed summaries, making it easier to stay updated with current research.

  9. Credit Card User Clustering

    This project involves clustering and segmenting around 9,000 active credit card users based on their behavior over a six-month period, using 18 behavioral variables. Customer data is preprocessed and reduced to two dimensions via Principal Component Analysis (PCA). K-Means clustering is then applied to group customers into four distinct clusters, enabling analysis of their behaviors and identification of cluster-specific characteristics.

  10. Predicting-Loan-Acceptance

    In this project, I had access to a bank dataset to predict which individuals the bank should target with personal loan offers based on historical data. I also employed machine learning models like Logistic Regression, Naive Bayes, and K-Nearest Neighbors, and assessed loan acceptance probabilities.

Skills

Programming Languages

Python

Java

C++

Ai Frameworks

Pytorch

TensorFlow

Keras

Scikit-Learn

LangChain

Huggingface

Data Visualization

Numpy

Pandas

Matplotlib

Seaborn

Web Development

HTML

CSS

PostgreSQL

Operating Systems

Linux(Ubuntu)

Windows

MacOs

Extra Tools

Git

Latex

Strong Background in

Machine Learning

Deep Learning

Computer Vision

AI agents

Natural Language Processing

Medical Imaging

Data Science