Skip to content
View sabin74's full-sized avatar
7 followers · 5 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report sabin74

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sabin74/README.md

Sabin Lamsal

Machine Learning Engineer | AI/ML Innovator

LinkedIn GitHub Portfolio Email Phone

About Me

I am an aspiring AI/ML Engineer passionate about building intelligent, real-world solutions.
With hands‑on experience in creating machine learning algorithms for crop disease detection, demand forecasting, recommendation systems, and credit risk analysis, I combine strong Python programming with deep knowledge of TensorFlow to solve problems in agriculture and finance.

📄 Download My Resume (PDF)

Technical Skills

Languages & Databases
Python SQL JavaScript PHP C C++

Data Science & Machine Learning
NumPy Pandas Scikit-learn TensorFlow Keras XGBoost Hugging Face OpenCV NLTK

Modeling Techniques
Supervised Learning Unsupervised Learning Ensemble Random Forest XGBoost Neural Networks CNN RNN LSTM Recommendation Systems Time‑Series ARIMA LSTM Forecasting Imbalanced Data

Visualization & Analysis
Matplotlib Seaborn Plotly EDA Statistical Analysis

Tools & Deployment
Git GitHub Jupyter Google Colab VS Code REST APIs Streamlit Docker

Professional Experience

Machine Learning Intern
Miss Misoo Production | Remote | January 2026 – May 2026

  • Engineered recommendation engines (popularity‑based, SVD, session‑based) achieving >20% accuracy improvement over baseline models.
  • Tackled cold‑start and sparsity challenges through hybrid and session‑based recommenders.
  • Developed two real‑time Streamlit web applications for movie and retail product recommendations.
  • Analyzed user behaviour to continuously enhance recommendation performance.

📜 Verification Documents:
 Internship Certificate
 Letter of Recommendation

Featured Projects

All projects are open‑source and available in separate repositories. Explore the full list on my GitHub profile.

Project & Link Description Core Technologies
Crop Disease Detection & Advisory System
Repo		 CNN achieving 96.18% accuracy on 45 diseases across 14 crops. Full‑stack MERN web application with bilingual (Nepali/English) disease diagnosis, treatment recommendations, PDF reports, and user dashboards. CNN, TensorFlow, MERN
AI‑Powered Movie Recommendation System
Repo		 Nine tuned models; best RMSE 0.8545 (23.5% improvement). Matrix factorization and hybrid techniques overcome 95% sparsity. Deployed with Streamlit on 1M+ ratings. SVD, Collaborative Filtering, Streamlit
Enterprise Demand Forecasting Platform
Repo		 Custom time‑series features (lags, rolling averages, holidays, oil prices) for store‑level sales prediction. Optimized RMSLE using XGBoost, LSTM, and GRU. Modular pipeline with configuration management. XGBoost, LSTM, GRU, Time‑Series
Loan Approval & Credit Risk Analysis
Repo		 Classification model for loan decisions; class imbalance handled with SMOTE. Evaluated with F1‑Score and ROC‑AUC. Production‑ready pipeline for fintech applications. Random Forest, SMOTE, Scikit‑learn
Traffic Sign Recognition
Repo		 Custom CNN and fine‑tuned MobileNetV2/VGG16 on GTSRB (43 classes). Achieved >97% accuracy using data augmentation and early stopping. CNN, Transfer Learning, TensorFlow, Keras

Education

Bachelor of Science in Information Technology / Computer Science
Bhaktapur Multiple Campus, Tribhuvan University
2023 – 2027 | Expected GPA: 3.48 / 4.0

Certifications & Professional Development

A comprehensive list of my verified certifications. Click the badge to view the official document.

Certificate Title Verification
Python for Data Science – Cognitive Class View
Machine Learning with Python – Cognitive Class View
Data Analysis with Python – Cognitive Class View
Data Visualization with Python – Cognitive Class View
Machine Learning with Python – freeCodeCamp View
Deep Learning with TensorFlow – Cognitive Class View
SQL and Relational Databases – Cognitive Class View
Accelerating Deep Learning with TensorFlow – Cognitive Class View

Let's Connect

I'm always open to new opportunities, collaborations, and conversations about AI/ML.

Email LinkedIn GitHub Portfolio

Pinned Loading

  1. Agriculture-Crop-Disease-Detection-Advisory-System Agriculture-Crop-Disease-Detection-Advisory-System Public

    Forked from Subodh-Dhamala/crop-disease-detection

    This project is a MERN-stack web application that uses CNN-based Machine Learning to provide early crop disease detection and prevention strategies. Specially tailored for Nepali agriculture, it al…

    Jupyter Notebook 1

  2. Movie-Recommendation-System Movie-Recommendation-System Public

    AI-powered Movie Recommender trained on 1 million real ratings. Get personalized suggestions in seconds. Built with Python, Streamlit, and scikit-learn during my ML internship at Miss Misoo Product…

    Jupyter Notebook 1

  3. Enterprise-Intelligent-Demand-Forecasting-Decision-Optimization-Platform Enterprise-Intelligent-Demand-Forecasting-Decision-Optimization-Platform Public

    This project focuses on building an end-to-end time series forecasting system to predict daily grocery sales for different product families across multiple stores. The goal is to leverage historica…

    Jupyter Notebook 1

  4. Loan-Approval-Prediction Loan-Approval-Prediction Public

    This project predicts whether a loan application will be approved or rejected based on applicant information and financial data. The goal is to build a binary classification model that accurately p…

    Jupyter Notebook 2

  5. Traffic-Sign-Recognition Traffic-Sign-Recognition Public

    This project focuses on building a deep learning model to classify traffic signs using Convolutional Neural Networks (CNNs). The model is trained on the German Traffic Sign Recognition Benchmark (G…

    Jupyter Notebook

  6. COVID-19_global_data_analysis COVID-19_global_data_analysis Public

    This project focuses on performing Exploratory Data Analysis (EDA) and time-series trend analysis on the global COVID-19 dataset provided by the Johns Hopkins University (JHU). It analyzes confirme…

    Jupyter Notebook