KVS's repositories
predicting_ticket_markups
Using Regression to Predict Concert Ticket Price Markups
tomorrow-theme
Tomorrow Theme the precursor to Base16 Theme
kaggle-airbnb
:earth_africa: Where will a new guest book their first travel experience?
distracted-drivers-keras
Starter project for the Kaggle State Farm Distracted Driver Detection Competition
datasci_course_materials
Public repository for course materials for the Data Science at Scale Specialization at Coursera
talktome
Machine learning lie detector
trading_machine_learning
Repository of project "Machine Learning for Trading"
kaggle-telstra
My code for Telstra Network Disruptions Kaggle competition
Compare-Models-Nested-X-Validation
A Python framework for comparing machine learning models with nested cross validation and receiver operator characteristic (ROC) curves. As an example, support vector machine (SVM) and logistic regression models are used to classify flower species of the Iris dataset, and the models are compared through nested cross validation and ROC curve analysis.
dlab-finance
Machine learning on the TAQ data
Python-for-Algorithms--Data-Structures--and-Interviews
Files for Udemy Course on Algorithms and Data Structures
aws_dashboard
Uses Python, Boto and Flask to output your EC2 instances, statuses and Name Tag if applicable.
mth-9879
Baruch course - Market Microstructure
factory-robot-simulator
Simulating a simple factory+robot scenario in Unity 5, in order to explore AI Methods to learn useful behavior.
Python_for_Finance
Python for Finance
Mastering_Python_for_Finance
Mastering Python for Finance
react-tour-of-heroes
Implementation of Angular 2's "Tour of Heroes" Tutorial in React
pyconuk-introtutorial
practical introduction to pandas and scikit-learn via Kaggle problems
Coursera-Cloud-Computing-Applications-Solution-Manual
My solution manual of Cloud Computing Applications course in Coursera.com
ML-algotrade
Algorithmic Trading with Machine Learning
ProFET
ProFET: Protein Feature Engineering Toolkit for Machine Learning
enron
In 2000, Enron was one of the largest companies in the United States. By 2002, it had collapsed into bankruptcy due to widespread corporate fraud. In the resulting Federal investigation, there was a significant amount of typically confidential information entered into public record, including tens of thousands of emails and detailed financial data for top executives. This project attempts to predict the likelihood of someone being a suspect of Enron fraud conspiracy by looking at given dataset. We call the suspects Person of Interest (POI). The dataset contains insider pays to all Enron executives as well as emails sent through their company accounts, and their POI status. We use machine learning to learn insider pays and emailing habits of POIs and non-POIs and see if we can find a pattern there, then use the model created to predict the likeliness of someone with a particular pattern of being a POI or not.
UCLA-CS-32
These are my solutions for the four projects and five homeworks from UCLA CS 32 Spring 2015 with Prof Smallberg. These are my own solutions and are therefore not perfect. The source code for the various projects should only be used as a vague guideline to help you if you are stuck. Do not copy directly from these files as they will result in your own penalisation!
dawp
Derivatives Analytics with Python (Wiley Finance)