Shreyaskumar Kathiriya's Projects
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
:books: Awesome CS Books(with Digests)/Series(.pdf by git lfs) Warehouse for Geeks, ProgrammingLanguage, SoftwareEngineering, Web, AI, ServerSideApplication, Infrastructure, FE etc. :dizzy: 优秀计算机科学与技术领域相关的书籍归档,以及我的读书笔记。
This repository consists of useful links for study materials for those aspiring carrer in AWS
Data Preprocessing, Exploratory Analysis with Visualisation on given stocks data to look for insights. (R language)
Advance distribution and usage statistical analysis on citibike data in New York City.
CitiBike Data analysis, Anomaly detection & neighborhood usage for better insights and proposing strategies.
Data visualisation practice on data provided in class to look for trends and valuable insights to curve the business.
Data analysis on sales of Progresso soup in the U.S.. Run regression analysis and other Data visualization techniques to look for insights and trends between factors like yearly seasons to support and provide Actionable business enhancing strategies.
Worked with student application data to practice concepts of Data preprocessing (EDA, Data cleaning and Imputation methods), feature engineering (Variable importance etc.), modeling (model tuning and split ratios) and model evaluation (Tree splits, F score, G score, Accuracy, Recall, Precision and Confusion Metrics. I made several models to compare and pick the one with best results.
Exploratory Data Analysis, Text Analytics and Sentimental Analysis on consumer complaint data along with other customer attributes. Looked for trends and insights to propose efficient customer handling strategies and key area to improve for better customer satisfaction.
A Collection of Cheatsheets, Books, Questions, and Portfolio For DS/ML Interview Prep
:bar_chart: Path to a free self-taught education in Data Science!
This tutorial playlist covers data structures and algorithms in python. Every tutorial has theory behind data structure or an algorithm, BIG O Complexity analysis and exercises that you can practice on.
The objective of this project was to Analyze and visualize the Election polling data and understand the direction of the election with major Breaking news and other Factors the move the polling outcomes between candidates.
Financial analysis and modelling on real world case studies dealing with merger and acquisitions and forecast value evaluation.
Industry Analysis and Global strategy practices used by Target Corp.
Graph Machine Learning, published by Packt
Various Graph theory case studies and Machine learning process Practiced in Data Engineering.
Studied impacts of Macro & Micro economy, consumer behavior using analytics techniques like Five Forces Model, Demand and Supply Analysis, Porter’s Competitive Strategy Framework PEST analysis and SWOT analysis for Target Corp
This project was an attempt to understand the top technology companies and the impact of stock market and its volatility. Here I worked with companies like Amazon, Google, Apple and Microsoft and find correlation between their stock prices and daily returns. I learned and implemented analysis methods like Monte Carlo, Bootstrap and 1000 simulated of stocks. The end goal was to put forward the learning of Data Analysis and Visualization in the field of Finance with the concepts I learned in Corporate finance.
Mastering spaCy, published by Packt
A repository to index and organize the latest machine learning courses found on YouTube.
This project was an attempt to understand and practice marketing concepts like funnel analysis and personal building to reach target audience. We used the provided email engagement data of students which consisted of key data points like “Open the email? Read the content? Click on links? Follow a call to action?” and several demographics, student test scores and school history data of the candidate. The goal of the project was to understand and Analyze the data and come up with strategies to target the Applicant students from prospect students using minimal resources and better the conversion rate.
Data Science Portfolio
In this project we joined together various dataset consisting data on student demographics, Course selection, Interaction with provided resources and past scores in other similar courses. The objective of the project was to predict a students likelihood of failing a certain courses before the end of the semester and provide them support to turn around the prediction. It will not only improve lives of many students but also grow university reputation with high passing rate and better education system.
This dataset was picked from one of the completions I participated on Kaggle, data is detailed information on passengers who were travelling on The Great Titanic and managed to either survive or die. The dataset had interesting story behind it and exploring the depths of it was an amazing experience. This was a fun practice project to strengthen my skills with Data Analysis and Visualization. The goal of the project was to explore various demographic parameters like a Age and Gender and look for connecting dots and stories that stands with the stats in the data. The final task was to train a model that predict if a passenger with certain characteristics would have survived or died in the incident.
Repository for the Big Data Specialization from University of California San Diego on Coursera
Key objective of the project was to account for reviews data on Amazon products to better the recommendation system and make recommendation more personalized. I made use of Amazon’s available data on products and customer reviews. The process included cleaning of the dataset followed by text analysis and sentimental analysis. The approach was quite clear, I broke the product reviews with key words (like shoes, comfortable, casual) and associated the product with these tag words. Further, I did the same for each reviewers by the reviews they gave and associated each reviewer with their key words extracted. Last application step was to recommend products to the user with their key words matching with the keywords of the product.