Santhosh Krishnan

Music Recommendation Systems operate through intricate algorithms that analyze vast amounts of data about users' musical interactions, such as their listening history, liked tracks, skipped songs, and even explicit user preferences conveyed through ratings or feedback. These data points are instrumental in constructing comprehensive user profiles, delineating individual tastes and preferences.

An end-to-end chatbot refers to a chatbot that can handle a complete conversation from start to finish without requiring human assistance. To create an end-to-end chatbot, you need to write a computer program that can understand user requests, generate appropriate responses, and take action when necessary. This involves collecting data, choosing a programming language and NLP tools, training the chatbot, and testing and refining it before making it available to users.

Instagram reach forecasting is the processing of predicting the number of people that an Instagram post, story, or other content will be reached, based on historical data and various other factors. For content creators and anyone using Instagram professionally, predicting the reach can be valuable for planning and optimizing their social media strategy. By understanding how their content is performing, creators can make informed decisions about when to publish, what types of content to create, and how to engage their audience.

The food chatbot project integrates Dialogflow for natural language understanding and FastAPI for backend services, enabling users to place and track orders through a website. It involves setting up intent recognition with Dialogflow, using MySQL for order management, and ensuring a smooth user experience from order entry to tracking.

This Projects contains code to build a Fashion Recommendation System utilizing image features. The system leverages computer vision and machine learning techniques to analyze fashion items' visual aspects like color, texture, and style and recommend similar or complementary products to users.

This Projects contains a Convolutional Neural Network (CNN) based plant disease classifier implemented using TensorFlow. The model is trained to classify plant images into three categories: "Healthy", "Powdery", and "Rust". The dataset consists of 1530 images divided into training, testing, and validation sets.

This project serves as a comprehensive guide to building an end-to-end data engineering pipeline using TCP/IP Socket, Apache Spark, OpenAI LLM, Kafka and Elasticsearch.

This Python-based project aims to fetch real-time YouTube metrics like likes, views, comments, and favorites, and then streams this data via Kafka. Also, KSqlDB was used for stream processing and the processed data is then sent to a Telegram bot for real-time notifications.

This Python project demonstrates how to enhance data manipulation and analysis using artificial intelligence with the pandas library. By integrating AI capabilities, you can supercharge your data tasks and gain deeper insights.

This Microsoft Fabric-based project enables real-time earthquake monitoring by automating data ingestion, processing, and visualization. Using Python, Data Factory, and Power BI, it fetches live earthquake data from the USGS API, transforms it following the Medallion architecture, and enriches it with location-based insights. The final dashboard offers interactive visualizations, allowing users to analyze seismic activity efficiently.