Wednesday, November 4, 2015

Introduction to Prediction Modeling

Cloud9 Charts now offers predictive analytics capabilities that can be applied to any data.

The data is passed through a variety of prediction models automatically - including Moving Average Models, Exponential Smoothing, Regressions and others - to determine the best fit based on historical data. 

Example: Let's take monthly stock prices for Amazon. The monthly stock prices looks like this:

Date, Price
06/01/16, 719.14
05/01/16, 683.85
04/01/16, 598.00
03/01/16, 579.00
02/01/16, 574.81
01/05/16, 633.79
12/01/15, 679.36
11/2/15, 628.35
10/1/15, 625.90
9/1/15, 511.89
8/3/15, 512.89
7/1/15, 536.15
6/1/15, 434.09
5/1/15, 429.23
4/1/15, 421.78
3/2/15, 372.10
2/2/15, 380.16
1/2/15, 354.53


1. Copy and paste the above dataset into https://www.cloud9charts.com/docs/predictive-analytics.html

2. Apply the following Cloud9QL into the query section:
select predict(Price, Date, 12/01/2015,1m,2)

This will backtest the dataset to determine the model with the best fit to then predict the price for future dates. (I hasten to add that historical data may not be always be a true indicator for future prices!)

Results:



Similar to the example above, you can predict any metric across any of your data.