Arpan Das's Projects
Profile Details
In this use case, we have developed a sample data pipeline (Glue Job) using the AWS typescript SDK, which will read the data from a dynamo DB table, perform some data transformation using PySpark and write it into an S3 bucket in CSV format.
In the life-cycle of insurance, when the insured incurred a loss and notify the insurer, the process in called FNOL (First Notice of Loss). When a FNOL hits the insurer'system it is important to identify the complexity of the claim. At present general insurance carriers spend almost 40% of the claim life cycle's time in the process of assigning and re-assigning the claims to the adjusters based on changing complexity level and adjuster's experience. Big insurance carriers sit on a gold mine of historical data, which can be utilized to predict the complexity of a claim using the power of machine learning/AI.
A standard Regression problem hosted by Club Mahindra to predict the Food and beverage spending of travelers at their resorts
This repository contains all the necessary files and data sets to analyze COVID-19 Outbreak
Customer Review Analysis is a prototype open source platform to turn the customer feedbacks in to visualization and extract the trending keywords.
Open-source demos hosted on Dash Gallery
A case study on how AI can help faster recovery from earthquake damages.The case study is modeled over Gorkha earthquake Nepal.Using the structural,geographical and legal data our task is to predict the severity of damage. Data Source: https://eq2015.npc.gov.np/
A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities
Insurance-RAG-Chatbot(IVA): An open-source project featuring a retrieval-augmented chatbot developed using Bedrock, LLM, LangChain, Docker, and more. Contribute to advancing insurance interaction with the power of open collaboration
Along with the other domains AI/ML is also growing to dominate the P&C Insurance market. In the business of 21st century identifying key customers and enriching customer relation is must for carriers for a descent ROI. 'Insurance Buddy' is a prototype chat bot to handle 360 degree customer queries, pre-sales product advertisements, customer policy validation, quick quote and help desk ticket generation. It is powered by googles NLU/NLP engine dialogflow, so can be easily integrated with google assistant, facebook, twitter, twillo etc. Tech Stack: DialogFlow, Node.Js, Firebase realtime DB, Kommunicate.
Deep Learning for humans
200 days of code commitment series: Solving leet code problems in python
Mask became an essential accessory post COVID-19. Most of the countries are making face masks mandatory to avail services like transport, fuel and any sort of outside activity. It is become utmost necessary to keep track of the adaptivity of the crowd. This repository contains implementation of a real time face mask adaptivity tracker using computer vision
This is a template for creating a Machine Learning application with its front-end developed using React which interacts with a Flask service as the back-end and makes predictions.
Workflow based prompt Chatbot developed on Microsoft bot framework (python SDK)
A nicer look at GitHub profiles built with Next.js and the GitHub API
ASP.Net Project on Online Examination Portal
Portfolio of projects I am working on
RAG-Chat-App
BFSI sectors deal with lots of unstructured scanned documents which are archived in document management systems for further use.For example in Insurance sector, when a policy goes for underwriting, underwriters attached several raw notes with the policy, Insureds also attach various kind of scanned documents like identity card, bank statement, letters etc. In later parts of the policy life cycle if claims are made on a policy, releted scanned documents also archeived.Now it becomes a tedious job to identify a particular document from this vast repository. The goal of this case study is to develop a deep learning based solution which can automatically classify scanned documents.
An autonomous car (also known as a driverless car, self-driving car, and robotic car) is a vehicle that is capable of sensing its environment and navigating without human input. Autonomous cars combine a variety of techniques to perceive their surroundings, including radar, laser light, GPS, odometry, and computer vision. Advanced control systems interpret sensory information to identify appropriate navigation paths, as well as obstacles and relevant signage
Serverless doc intake is an AWS backed serverless document ingestion engine which helps digitize manual documents and saves time