Team Members

Vamshidhar Reddy Kanamanthareddy
Ankit
Sai Charan Pappala
Uday Kolli

Data

The data is sourced from https://www.alphavantage.co/documentation/ and we are predicting the close price.

• Primary data The primary data is Intraday stock details with 60 mins Time Intervals. It has 5 predictors
  1.open
  2.high
  3.low
  4.close
  5.volume

• Secondary data We are planning to use:
  Fundamental (INCOME STATEMENT)
  Economic (CONSUMER SENTIMENT)
  Technical Indicators (SMA, EMA, RSI, ADX, STOCH etc.)
  to enrich our data set and using these as part of our prediction.

• How will you collect all the data We retrieve the data form various API’S provided by https://www.alphavantage.co/documentation/

• How will you clean and transform the data We will make use for packages base R , Tdiyverse, dplyr to clean and format our data

Problem Description

Stock market prices are very volatile and every investor is interested to know it’s future behavior so that they can invest and gain profits. Prediction and analysis of Stock prices are some of the most difficult jobs to complete. There can be various reasons for this like market fluctuations, news, customer sentiments, pandemic etc. We would like to consider some of these factors as our predictors and would like to come up with a prediction of stock price.

Analytics plan

As part of our analytically plan we would follow below actions:

• We will be enriching our primary data set with data/predictors obtained from other API’s
  
• Identifying and handling missing values
  
• Identifying and handling outliers
  
• Identifying and handling categorical variables
  
• Split data into Training and Validation sets
  
• Scale/Normalize data in cases of huge variations
  
• Visualize data to have a better understanding of each of the above points
  
• We are planning to use Random Forest or PCA initially to identify the variable importance among our predictors
  
• We are planning to use LTSM for our model training and any other model which suits our time-series regression use case
  
• We will try to use hyperparameter tuning to find the ideal parameter for model

Evaluation plan

As part of our evaluation plan we would like to perform below actions:

• We will evaluate by plotting the results between actual and predicted values
  
• We will compare the results using MAPE / RMSE / R-squared / Adjusted R-squared
  
• We will conclude with the outcome of our models