ishan2205/vit_hack

Challenge 1: Fundamental Analysis on Financial data

There are about 4000 stocks which are actively traded on the stock exchanges at BSE and NSE. Can we extract public financial data from sites like moneycontrol.com to find which are the fundamentally strong stocks. On what stocks would the father of value investing, Benjamin Graham and Warren Buffett the most successful investors in the world make their investments on. Benjamin Graham and Warren Buffett Model Step 1: Filter out all companies with sales less than Rs 250 cr. Companies with sales lower than this are very small companies and might not have the business stability and access to finance that is required for a safe investment. This eliminates the basic business risk. Step 2: Filter out all companies with debt to equity greater than 30%. Companies with low leverage are safer. Step 3: Filter out all companies with interest coverage ratio of less than 4. Companies with high interest coverage ratio have a highly reduced bankruptcy risk. Step 4: Filter out all companies with ROE less than 15% since they are earning less than their cost of capital. High ROE companies have a robust business model, which generates increased earnings for the company typically. Step 5: Filter out all companies with PE ratio greater than 25 since they are too expensive even for a high-quality company. This enables us to pick companies which are relatively cheaper as against their actual value. He points out that applying these filters enables us to reduce and even eliminate a lot of fundamental risks while ensuring a robust business model, strong earning potential and a good buying price..

Challenge 2: Sentiment Analysis on News data.

Can we use the content of news analytics to predict stock price performance? The ubiquity of data today enables investors at any scale to make better investment decisions. The challenge is ingesting and interpreting the data to determine which data is useful, finding the signal in this sea of information. Deevia is passionate about this challenge and is excited to share it with the community. By analyzing news data to predict stock prices, you have a unique opportunity to advance the state of research in understanding the predictive power of the news. This power, if harnessed, could help predict financial outcomes and generate significant economic impact all over the world.

Challenge 3: Time series prediction of stock prices

The neural network are one of the intelligent data mining technique that has been used by researchers in various areas for the past 10 years. Prediction and analysis of stock market data have got an important role in today’s economy. Can we use different types of deep learning architectures like Multilayer Perceptron (MLP), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) for predicting the stock price of a company based on the historical prices available. Here we are using day-wise closing price of National Stock Exchange (NSE). Using Tensor flow and keras library in python.