Created different models that will help predict if the borrower has a high probability of paying their loan back in full and analyze the performance to choose the most suitable model.

This is Python 3 based project to perform fast & accurate face detection with OpenCV using a pre-trained deep learning face detector model shipped with the library.

Exploring Fusion Adaptive Resonance Theory to store data, represent knowledge and predict results under noise using natural language processing.

RPS GameOn: In these project, I created a "Rock Paper Scissors" game as GUI application using python Tkinter library.

TUDelft-CSE-research-project

Using Logistic regression algorithm for predicting whether the patient has heart disease or not.

KisaanBot: A chatbot assistant for farmers towards improving livelihood

Create a model that can accurately predict whether a user belongs to the HCP(Healthcare Professional) category or not. Based on server logs.

End-to-end projects: customer churning prediction using the Random Forest Classifier Algorithm with 97% accuracy; performing pre-processing steps; EDA and Visulization fitting data into the algorithm; and hyper-parameter tuning to reduce TN and FN values to perform our model with new data. Finally, deploy the model using the Streamlit web app.

Evidence-Based Scheduler

Implementing Neural Network on Irish data - evaluating accuracy, Mean Squared Error (MSE), Crossentropy and log-likelihood

Using Runge-Kuttah algorithm to solve a wide variety of differential equations

What is "accuracy"? The effect of changing the decision threshold on a model's accuracy.

This work proposes a new approach for detecting fake news in datasets using some of the most widely used algorithms of machine learning.

This is a mini project on Brain Stroke Prediction using ML Classification Algorithm(Logistic Regression)

kNN algorithm implementation in Python with graphical analysis

[Tutorial] Start off with a simple convolutional network to use on the CIFAR-10 dataset, followed by several adjustments to increase the accuracy to >92%.

Titanic : Machine Learning from Disaster