chiragsoni95 Goto Github PK
Name: ChiragSoni
Type: User
Company: Ernst and Young US LLP
Bio: Machine Learning Engineer
Location: Cambridge, MA
Name: ChiragSoni
Type: User
Company: Ernst and Young US LLP
Bio: Machine Learning Engineer
Location: Cambridge, MA
:trophy: Automatically grade english essays using NLP techniques (This is not a ML model).
A website to display my work, interests and my web development skills. My Link: https://ChiragSoni95.github.io
This repository contains coding interviews that I have encountered in company interviews
added all materials
Parallel Programming lab assignments and projects using High Performing Clusters called Extreme provided by UIC ACCC powered by Acer Labs.
Loan Application Expert system is a rule based expert system designed using FUZZY JESS wherein information of a loan applicant is asserted by the user of the Bank, and finally concludes whether applicant is eligible to apply for a loan or not. System also provides suggestions to the user of the system to help him/her to make a decision in a very convenient manner. The expert system checks for all the boolean and Fuzzy parameters asserted by the user and finally claims the decision depending upon its interpretation and a few important rules set in the bank’s policy.
GeeksforGeeks Algorithms and Questions implemented in Python
You are working for a non-profit that is recruiting student volunteers to help with Alzheimer’s patients. You have been tasked with predicting how suitable a person is for this task by predicting how empathetic he or she is. Using the Young People Survey dataset (https://www.kaggle.com/miroslavsabo/young-people-survey/), predict a person’s “empathy” on a scale from 1 to 5. You can use any of the other attributes in the dataset to make this prediction.
Implementation of semantic segmentation of FCN structure using kitti road dataset. I used a tensorflow and implemented a segmentation algorithm with a mean-iou score of 0.944.
Loan Application Expert system is a rule based expert system designed using JESS wherein information of a loan applicant is asserted by the user of the Bank, and finally concludes whether applicant is eligible to apply for a loan or not. System also provides suggestions to the user of the system to help him/her to make a decision in a very convenient manner. The expert system checks for all the parameters asserted by the user and finally claims the decision depending upon its interpretation and a few important rules set in the bank’s policy.
Models and examples built with TensorFlow
MSApriori algorithm is capable of classifying rare classes. The performance evaluation of the proposed algorithm has been done for different data sets and in comparison with existing technique like Apriori algorithm it is found that algorithm has efficient and superior performance for classifying rare cases.
Bayesian Network designed using NETICA wherein information of different type of loan applicants and types of loan is asserted by the user of the Bank, and finally concludes whether applicant will be to repay loan or not.
Loan Repayment Decision system is a combination of Bayesian Network and influence Diagram designed using NETICA wherein information of different type of loan applicants and types of loan is asserted by the user of the Bank, and finally concludes whether applicant will be to repay loan or not.Accurately predicting whether a loan will be repaid (credit" scoring) is an important task for any bank.Furthermore, the decision regarding the deadline if it needs to be extended or not is made using the utility and decision node in influence diagram. High accuracy benefits both the banks and the loan applicants.
First neural network model using the powerful Keras Python library for deep learning.
Examples, Assignments and Application developed during the course NodeJS, Express and MongoDB
Project management scrum tool for developers and managers following agile programming methodology
Offline Voting Application
Android Online Learning Application
Graduate course project which provides experience in creating a generator that creates a syntactically correct but semantically meaningless Java Program
React application developed during the course Front-end development with ReactJS
Building professional REST APIs with Python, Flask, Flask-RESTful, and Flask-SQLAlchemy
RSSNewsFeed Android Application
Deep learning neural network model to recognize numbers from 0 to 5 in sign language with a pretty impressive accuracy of 95% on training data and 72% on the test data
:trophy: System for recognizing and tracking patterns within data so as to not only react but also anticipate the customer needs in advance.
Determine the common bugs after analyzing pattern of patches for various issue/bug reports
Monte Carlo simulator on a Octa Pi cluster using Spark and Kubernetes
A REST API to access items, stores, user authentication.
Given a collection of tweets, classify them into four classes namely: positive, negative, neutral and mixed. The tweets used here are pertaining to two US presidential candidates namely: Barack Obama and Mitt Romney. By classifying the tweets into the mentioned classes we would be capable of predicting the opinion of the public and get a sense of the outcome of the election.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.