Pinned Repositories
Bank-Customer-Churn-Prediction-
Bank Customer Churn Prediction with Decision Tree, Random forest, Logistic Regression, KNN (K-Nearest Neighbor), and Voting Classifier.
BERT-Fine-Tuning-and-AWS-Comprehend-for-Multi-label-Text-Classification
The web scraping code extracts detailed product information, forming the foundation for ML-based categorization. Two methods are implemented for assigning category tags to products based on their titles. Model 1: Advanced Custom Classification in AWS Comprehend. Model 2: Fine-tuned BERT Language Model.
Car-Parts-Competitive-Analysis-NLP-Tableau-Clustering
Applied NLP for automated categorization of products, aligning Amazon items with CARiD’s category framework. Conducted significant statistical analysis to unearth factors influencing product popularity and sales. Segmented automotive products into five clusters, ranging from "Basic Needs" to "Premium Selections", enabling targeted marketing.
Customer-Behavior-Analysis
Default-prediction-unisng-LR-with-validation-set-approach
logistic regression is used to predict the probability of default using income and balance on the Default data set. I also estimated the test error of this logistic regression model using the validation set approach.
Fetal-Health-Classification-with-Pyspark
Fetal-Health-Classification-with-Python
SNA-for-a-novel-analysis
Book analysis using social network analysis
SolarPanel_Detection_on_rooftops_using_Image_Processing
In this project which won the PRME Award at Clark University Analytics competition, I used a U-Net encoder-decoder which has been initialized with ResNet50 to detect buildings with Solar Panel on their rooftops on NewYork city and Worcester, MA. Using image processing, we are able to automatically detect the solar panel distribution over cities.
Timeseries_Quarterly-Coal-Power-Analysis
A comprehensive analysis using AR, MA, ARMA, and ARIMA models for quarterly coal power consumption forecasting. This work delves into data preprocessing, stationarity testing, trend and seasonality analysis, and predictive modeling to aid energy sector decision-making and policy formulation.
Maryamahmadii's Repositories
Maryamahmadii/BERT-Fine-Tuning-and-AWS-Comprehend-for-Multi-label-Text-Classification
The web scraping code extracts detailed product information, forming the foundation for ML-based categorization. Two methods are implemented for assigning category tags to products based on their titles. Model 1: Advanced Custom Classification in AWS Comprehend. Model 2: Fine-tuned BERT Language Model.
Maryamahmadii/SolarPanel_Detection_on_rooftops_using_Image_Processing
In this project which won the PRME Award at Clark University Analytics competition, I used a U-Net encoder-decoder which has been initialized with ResNet50 to detect buildings with Solar Panel on their rooftops on NewYork city and Worcester, MA. Using image processing, we are able to automatically detect the solar panel distribution over cities.
Maryamahmadii/Car-Parts-Competitive-Analysis-NLP-Tableau-Clustering
Applied NLP for automated categorization of products, aligning Amazon items with CARiD’s category framework. Conducted significant statistical analysis to unearth factors influencing product popularity and sales. Segmented automotive products into five clusters, ranging from "Basic Needs" to "Premium Selections", enabling targeted marketing.
Maryamahmadii/Default-prediction-unisng-LR-with-validation-set-approach
logistic regression is used to predict the probability of default using income and balance on the Default data set. I also estimated the test error of this logistic regression model using the validation set approach.
Maryamahmadii/Fetal-Health-Classification-with-Pyspark
Maryamahmadii/SNA-for-a-novel-analysis
Book analysis using social network analysis
Maryamahmadii/Bank-Customer-Churn-Prediction-
Bank Customer Churn Prediction with Decision Tree, Random forest, Logistic Regression, KNN (K-Nearest Neighbor), and Voting Classifier.
Maryamahmadii/Customer-Behavior-Analysis
Maryamahmadii/Fetal-Health-Classification-with-Python
Maryamahmadii/Fire-Detection-for-AI-based-Smoke-Detector-Device
Maryamahmadii/Image-Classification-MNIST-Dataset
Training a deep learning model to correctly classify hand-written digits.
Maryamahmadii/K-NN-Logistic-Reg_Car-s-gas-mileage-prediction
Developing K-NN and Logistic Regression models to predict whether a given car gets high or low gas mileage based on the Auto data set.
Maryamahmadii/STAT-class
Project
Maryamahmadii/Timeseries_Quarterly-Coal-Power-Analysis
A comprehensive analysis using AR, MA, ARMA, and ARIMA models for quarterly coal power consumption forecasting. This work delves into data preprocessing, stationarity testing, trend and seasonality analysis, and predictive modeling to aid energy sector decision-making and policy formulation.
Maryamahmadii/Transaction-Based-Financial-Fraud-Detection
An Object-Oriented Framework for Financial Fraud Detection in Python. Created a framework to deploy various anomaly detection and classification algorithms for model analysis.
Maryamahmadii/Azure-document-intelligence-check-sample
Maryamahmadii/mslearn-knowledge-mining
Lab files for Azure AI Knowledge Mining modules