Hi, I’m Anu Joshi, a Data Scientist passionate about transforming data into actionable insights. With a strong background in machine learning, deep learning, geospatial analysis, and data visualization, I specialize in applying Python, Power BI, and GIS to solve real-world problems across multiple industries.

I am currently pursuing my Master of Science in Data Science at the University of Boston and completed MIT’s Applied Data Science Program, where I’ve gained hands-on experience in AI, ML, and recommendation systems. My work spans climate science, business analytics, healthcare and marketing, leveraging data-driven strategies to optimize decision-making.

◾Boston House Price Prediction – Repository Leveraged machine learning and regression modeling to forecast housing prices, uncover key price drivers, and enhance investment insights.

◾ Automotive Pricing Analysis – Repository Leveraged regression and tree-based models to identify key customer segments

◾ Business Data Analysis: Restaurant Demand Forecasting – Repository Optimized restaurant performance using SQL and Python to identify customer demand trends.

◾ Vaccine Marketing Strategy : N1H1 - Repository Optimized target market on who should be approached to receive the N1H1 vaccine and how resources should be allocated.

◾ Pneumonia X-ray Detection – Repository Built a convolutional neural network (CNN) for medical image classification

More Projects Coming Soon!

✔ Programming & Data Analysis: Python (Pandas, NumPy, Scikit-Learn), SQL, ✔ Machine Learning & AI: Deep Learning, Time Series Forecasting, Recommendation Systems ✔ Data Visualization: Power BI, Matplotlib, Seaborn ✔ Big Data & Cloud: AWS, ✔ Geospatial Analysis: GIS, ArcGIS.

Algorithms I Have Experience With

I have worked with a wide range of machine learning, deep learning, and statistical algorithms, applying them to real-world datasets across marketing, healthcare, business analytics, and climate science. Below is a categorized list of the algorithms I have experience with:

🔹 Supervised Learning Algorithms ✔ Linear Regression – Predicting continuous outcomes (e.g., sales forecasting, house prices) ✔ Logistic Regression – Binary classification problems (e.g., fraud detection, churn prediction) ✔ Decision Trees – Intuitive classification and regression models ✔ Random Forest – Ensemble learning for improved accuracy and stability ✔ Gradient Boosting (XGBoost, LightGBM, CatBoost) – High-performance predictive modeling ✔ Support Vector Machines (SVM) – Complex classification problems ✔ k-Nearest Neighbors (k-NN) – Instance-based learning for pattern recognition

🔹 Unsupervised Learning Algorithms ✔ K-Means Clustering – Customer segmentation, market analysis ✔ Hierarchical Clustering – Identifying natural groupings in data ✔ DBSCAN – Density-based clustering for anomaly detection ✔ Principal Component Analysis (PCA) – Dimensionality reduction for feature selection ✔ t-SNE & UMAP – High-dimensional data visualization

🔹 Time Series & Forecasting Models ✔ ARIMA (AutoRegressive Integrated Moving Average) – Time series forecasting ✔ SARIMA & Prophet – Seasonal time series forecasting ✔ LSTMs (Long Short-Term Memory Networks) – Deep learning for sequential data

🔹 Deep Learning & Neural Networks ✔ Feedforward Neural Networks (FNNs) – Basic neural network architectures ✔ Convolutional Neural Networks (CNNs) – Image classification and feature extraction ✔ Recurrent Neural Networks (RNNs) – Sequential data analysis ✔ Transformers (BERT, GPT, T5) – Natural Language Processing (NLP) ✔ Autoencoders – Anomaly detection, feature engineering ✔ GANs (Generative Adversarial Networks) – Synthetic data generation

🔹 Recommendation Systems ✔ Collaborative Filtering (User-Based & Item-Based) – Personalized recommendations ✔ Matrix Factorization (SVD, ALS) – Latent factor modeling ✔ Hybrid Recommendation Systems – Combining multiple techniques

🔹 Anomaly Detection & Optimization ✔ Isolation Forest – Detecting rare events and anomalies ✔ One-Class SVM – Outlier detection in high-dimensional data ✔ Genetic Algorithms – Optimization and search problems

I have applied these algorithms using Python (Scikit-Learn, TensorFlow, PyTorch, XGBoost, StatsModels,) and have optimized models for business intelligence, climate data science.

📧 Email:anujoshi3390@gmail.com LinkedIn: linkedin.com/in/anuradhasjoshi

Looking for exciting data science collaborations or career opportunities? Feel free to reach out—I’d love to chat!