AIML Projects

Artificial Intelligence and Machine Learning (AIML) Projects

Project Category	Domain; Industry	Description	Tools and Technologies Used	Skills Used	Content; Documentation	GH Repo
Applied Statistics	"Marketing, Manufacturing, Sports, Start-up Ecosystem"	Performed detailed statistical analysis and EDA using univariate, bi-variate and multivariate EDA techniques to get data driven insights on recommending improvements and suggestions to the management.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib	Data Preprocessing, Probability and Statistics, Descriptive Statistics, Inferential Statistics, Multivariate Analysis; Critical Thinking, Problem-Solving, Communication Skills, Collaboration; Time Management, Documentation, Version Control Systems	Content	Repo
Supervised Learning	"Medical, Banking, Marketing"	Demonstrated the ability to fetch, process and leverage data to generate useful predictions by training Supervised Learning algorithms. Built Machine Learning models to perform focused marketing by predicting the potential customers who will convert using the historical dataset.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Flask	Data Pre-processing, EDA, Classification, Regression, Model Evaluation, Model Selection, Overfitting, Underfitting, Feature Engineering, Hyperparameter Optimization	Content	Repo
Unsupervised Learning	Automobiles	Developed and understood the K-means Clustering by applying on the Car Dataset to segment the cars into various categories. Applied the dimensionality reduction technique – PCA, trained a model, and compared the relative results for clustering.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Flask, Rapidminer, DataIku, Weka	Data Pre-processing, EDA, K-Means Clustering, Hierarchical Clustering, DBSCAN, Principal Component Analysis (PCA), Association Rule Learning, Anomaly Detection, Model Evaluation, Model Selection, Overfitting, Underfitting, Feature Engineering, Hyperparameter Optimization, Model Deployment	Content	Repo
Ensemble Learning Methods	"Telecommunications, Information Technology"	Built a model that help to identify the potential customers who have a higher probability to churn. Built a machine learning workflow that run autonomously with the csv file and return best performing model.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Flask, Rapidminer, DataIku, Weka, SQL Server	Data Pre-processing, EDA, Bagging, Boosting, Voting, Stacking, Bootstrapping, Model Evaluation, Model Selection, Overfitting, Underfitting, Feature Engineering, Hyperparameter Optimization, Model Deployment	Content	Repo
Feature Engineering	Manufacturing	Developed a classifier to predict the Pass/Fail yield of a particular process entity and analyse whether all the features are required to build the model or not.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Flask, Rapidminer, DataIku, Weka, Microsoft Azure	Data Pre-processing, EDA, Bagging, Boosting, Feature Creation, Feature Selection, Feature Scaling, Feature Encoding, Dimensionality Reduction, Automated Feature Engineering, Overfitting and Underfitting, Model Interpretation, Model Evaluation, Model Selection, Overfitting, Underfitting, Feature Engineering, Hyperparameter Optimization, Model Deployment	Content	Repo
Hyperparameter Optimization	Manufacturing	Developed a classifier to predict the Pass/Fail yield of a particular process entity and analyse whether all the features are required to build the model or not.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Flask, Rapidminer, DataIku, Weka, AWS Sagemaker	Data Pre-processing, EDA, Bagging, Boosting, Feature Creation, Hyperparameters and Parameters, Cross Validation, Grid Search, Random Search, Bayesian Optimization, Model Performance and Complexity, Overfitting, Underfitting, Feature Engineering, Hyperparameter Optimization, Model Deployment	Content	Repo
Recommender Systems	"Ecommerce, Electronics"	Implemented a recommendation system using popularity based and collaborative filtering methods to recommend mobile phones to a user which are most popular and personalised respectively.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Surprise, Flask, Rapidminer, DataIku, Weka	Data Pre-processing, EDA, Model Evaluation, Model Selection, Association Rule Learning, Content-based Filtering, Collaborative Filtering, Hybrid Methods, Cold Start Problem, Scalability, Privacy and Ethics, Model Interpretation and Explanation, Deep Learning-based Recommenders, Graph-based Recommenders, Context-aware Recommenders	Content	Repo
Deep Learning Systems	"Electronics and Telecommunication, Autonomous Vehicles"	Developed a classifier model which can use the given parameters to determine the signal strength or quality. Built a digit classifier on the SVHN (Street View Housing Number) dataset.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Seaborn, Tensorflow, Keras, Google Colab, Azure ML, AWS Sagemaker	Data Pre-processing, EDA, Classification, Regression, Model Evaluation, Model Selection, Overfitting, Underfitting, Hyperparameter Optimization, Neural Networks, Activation Functions, Deep Neural Networks, CNN, RNN, LSTM, GANs, Transformer Networks, Attention Mechanisms, Transfer Learning, Model Interpretation and Explanation, Data Requirements, Ethical and Societal Issues, Computational Resources, Future Trends	Content	Repo
Natural Language Processing (NLP) - 1	"Digital Content Management, Customer Support"	Implemented an NLP classifier which can use input text parameters to determine the label/s of the blog. Designed a python based interactive semi - rule based chatbot	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Seaborn, Tensorflow, Keras, NLTK, SpaCy, Transformers, Gensim, Google Colab, Azure AI/ML	Data Pre-processing, EDA, Classification, Regression, Model Evaluation, Model Selection, Overfitting, Underfitting, Hyperparameter Optimization, Neural Networks, Activation Functions, Deep Neural Networks, Tokenization, POS Tagging, NER, Parsing, Sentiment Analysis, Machine Translation, Text Summarization, Topic Modeling, Text Classification, Word Embeddings, Search Engines, Chatbots and Virtual Assistants, Text to Speech, Speech to Text	Content	Repo
Natural Language Processing (NLP) - 2	"Digital Content and Entertainment Industry, Social Media Analytics"	Implemented a sequential NLP classifier which can use input text parameters to determine the customer sentiments. Developed a sequential NLP classifier which can use input text parameters to determine the customer sentiments.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Seaborn, Tensorflow, Keras, NLTK, SpaCy, Transformers, Gensim, Google Colab, AWS Sagemaker	Data Pre-processing, EDA, Classification, Regression, Model Evaluation, Model Selection, Overfitting, Underfitting, Hyperparameter Optimization, Neural Networks, Activation Functions, Deep Neural Networks, RNN, GRU, LSTM, BERT, Classical ML, Tokenization, POS Tagging, NER, Parsing, Sentiment Analysis, Machine Translation, Text Summarization, Topic Modeling, Text Classification, Word Embeddings, Search Engines, Chatbots and Virtual Assistants, Text to Speech, Speech to Text	Content	Repo
Computer Vision Systems (CV) - 1	Botanical Research	Developed a classifier to predict the type of leaf using image data. Built a model to identify plant diseases based on leaf images.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Seaborn, Tensorflow, Keras, OpenCV, PyTorch, FastAI, DVC, Google Colab, Azure AI/ML, AWS Sagemaker	Data Pre-processing, EDA, Image Processing, Feature Extraction, CNNs, Transfer Learning, Image Classification, Object Detection, Image Segmentation, Facial Recognition, Medical Imaging, Data Augmentation, Data Annotation, Computer Vision Algorithms, Model Training, Project Management, Documentation, Responsible AI, Document Intelligence, Model Deployment, Azure Databricks, Source Control Management, Generative AI	Content	Repo
Computer Vision Systems (CV) - 2	Entertainment, Face Recognition	Developed a face recognition system using OpenCV and Dlib libraries. Built a model to identify characters from video frames for metadata generation.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Seaborn, Tensorflow, Keras, OpenCV, Dlib, PyTorch, FastAI, DVC, Google Colab, AWS Sagemaker	Data Pre-processing, EDA, Image Processing, Feature Extraction, CNNs, Transfer Learning, Image Classification, Object Detection, Image Segmentation, Facial Recognition, Data Augmentation, Data Annotation, Computer Vision Algorithms, Model Training, Project Management, Documentation, Responsible AI, Document Intelligence, Model Deployment, AWS Lambda, API Gateway, Source Control Management, Generative AI	Content	Repo
Computer Vision Systems (CV) - 3	Healthcare	Developed a classifier to predict the disease type using MRI scan images. Built a model to identify cancerous cells in histopathological images.	Python, Numpy, Pandas, SciPy, Statsmodels, Scikit-learn, Matplotlib, Seaborn, Tensorflow, Keras, OpenCV, PyTorch, FastAI, DVC, Google Colab, Azure AI/ML, AWS Sagemaker	Data Pre-processing, EDA, Image Processing, Feature Extraction, CNNs, Transfer Learning, Image Classification, Object Detection, Image Segmentation, Medical Imaging, Data Augmentation, Data Annotation, Computer Vision Algorithms, Model Training, Project Management, Documentation, Responsible AI, Document Intelligence, Model Deployment, Azure Databricks, Source Control Management, Generative AI	Content	Repo