I'm a passionate software engineer with a First Class Bachelor's degree in Computer Science from the University of Surrey,
specializing in Python, machine learning, and automation. With 2 years of experience, including impactful work at Jaguar Land Rover,
I deliver innovative solutions to complex problems. Whether it's developing efficient automation scripts, diving deep into data analysis,
or pioneering machine learning models for image processing,
I'm here to turn your ideas into reality with my blend of technical expertise and creative problem-solving.
Beyond the code, I'm deeply engaged with the latest tech trends, an avid sports fan, and a curious explorer of both digital innovations and the great outdoors.
My portfolio is a reflection of my commitment to innovation, efficiency, and continuous learning, showcasing projects that blend technical prowess with creative problem-solving.
This project aims to analyse and predict customer churn for a telecom company using the Telco Customer Churn dataset. The primary goal is to identify the factors that contribute to customer churn and develop a predictive model to forecast which customers are likely to leave the company. The insights gained from this analysis can help the company implement targeted retention strategies.
This Face Recognition project is designed to provide efficient face detection and recognition capabilities using advanced computer vision techniques. The system offers two primary functionalities: static face recognition, which processes single captured photos, and live face recognition, which operates in real-time using a video feed. The project leverages a combination of modern software libraries and pre-trained models to achieve high accuracy and performance.
Machine learning models that are based on decision trees have gained popularity because of their simplicity, interpretability, and utility. However, it is often observed that these models experience a reduction in accuracy and an escalation in intricacy, leading to suboptimal performance and excessively large tree sizes. The aim of this study is to improve the structure of decision trees through the application of genetic algorithms and to enhance their effectiveness by utilising deep neural networks for the purpose of feature extraction.
My notebook from a university class Kaggle competition to classify types of flowers from images. I got 2nd place (out of 69 students) with an accuracy of 99.13%
For this project we set out to develop an image classifier that could classify an image of a lesion and predict what type of lesions it is from a list of seven common types (Actinic keratoses (akiec), Basal cell carcinoma (bcc), Benign keratosis-like(bkl), Dermatofibroma (df), Melanoma(mel), Melanocytic nevi(nv), Vascular lesions(vasc)). One of our key aims for this project was to develop a classifier that not only gave the user a prediction but would also output an image showing the user what features of the image the classifier had used to make its prediction.
Sentiment Analysis of 50k IMDB movie reviews.
A flutter app for testing True/False trivia knowledge. The app counts the number of correct questions and pulls the questions using an API call from opentbd.
Connect with me on LinkedIn or send me an email.