PRODIGY INTERNSHIP - MACHINE LEARNING

I extend my sincerest appreciation to Prodigy Infotech for granting me the opportunity to delve into these projects and for their unwavering support and guidance throughout my internship journey. Below, I outline my methodology for tackling the assigned tasks.

TASK 1: House Price Prediction

In this endeavor, I crafted a straightforward linear regression model aimed at predicting house prices based on key metrics like square footage, number of bedrooms, and bathrooms.

TASK 2: Customer Segmentation

My focus here revolved around segmenting retail store customers by employing K-means clustering. Leveraging synthetic purchase history data, I clustered customers based on their buying frequency and total expenditure. By discerning distinct customer segments, tailored marketing strategies and product offerings can be devised, enhancing the store's effectiveness.

TASK 3: Cat vs Dog

Implementing a Support Vector Machine (SVM) classifier, I tackled the classification of cat and dog images using the TensorFlow Datasets (TFDS) Cats vs Dogs dataset. After preprocessing and normalization, the SVM model was trained and tested on subsets of the dataset, showcasing its prowess in image classification tasks.

TASK 4: Hand Gesture Recognition

With a focus on intuitive human-computer interaction, I embarked on developing a model for accurately recognizing and classifying various hand gestures from image or video data. By employing convolutional neural networks (CNNs), the model is trained on diverse hand gesture data, enabling seamless interaction between users and devices.

TASK 5: Food Recognition

This project aims to develop a robust model for accurately recognizing food items from images and estimating their calorie content. Through the utilization of convolutional neural networks (CNNs) on a diverse food image dataset, the model facilitates informed dietary choices by providing estimated calorie values, thereby aiding users in maintaining a healthy lifestyle.