1-844-696-6465 (US)        +91 77600 44484        help@dezyre.com

# Match the right Time Series Forecasting Methods to the right Business Problems

There are various methods to forecast stock price, demand etc. which method/technique to be used when and how to apply the forecasting methods.
4.94.9

## What will you learn

• Understanding the importance of time series
• Understanding the mathematics of time series
• Application of the models using R or Python
• Making conclusions

## What will you get

• Access to all material related to project like data files, solution files etc.

## Prerequisites

• Jupyter Notebook from Anaconda installation
• R (3.3.3) and R-Studio (1.4) installation
• At least 4 GB RAM Machine

## Project Description

In this hackerday, we will be taking open source data that are publicly available and will be discussing various methods/techniques of performing time series forecasting. We will be talking about the traditional methods such as holt-winters method, Autoregressive integrated moving average method, exponential smoothing methods, as well as we will be comparing the modern methods of performing forecasting using neural network based models.

## Curriculum For This Mini Project

What is Time Series
00:04:22
How to create Time Series in R
00:05:11
Components of Time Series
00:03:49
Assumptions of Time Series Forecasting
00:05:19
Investigate components of Time Series
00:02:30
Example - Stock Market Dataset
00:01:41
00:03:30
STL method
00:02:36
Plot graph for Decompose and STL function
00:01:33
How to do Time Series Forecasting
00:08:01
Create Time Series Lag
00:10:52
00:02:03
Identify AutoCorrelation
00:11:18
Partial Autocorrelation
00:01:57
DeTrend a Time Series using Johnson method
00:07:47
Deseasonalize Time Series
00:05:21
Seasonality Plot
00:03:00
00:03:29
KPSS Test
00:02:29
Air Passenger Data - ADF Test
00:01:31
Differencing Method
00:17:53
Moving Average Method
00:04:22
Data Visualization
00:01:47
Forecast Methods
00:03:22
Moving Average Method
00:06:59
Exponential Smoothing Method
00:01:11
Simple Exponential Smoothing Method
00:06:34
Double Exponential Smoothing Method
00:01:17
Triple Exponential Smoothing Method
00:01:25
Compare accuracy of models
00:07:03
Generate forecast using all 3 methods
00:03:50
Arima - Auto Regressive Integrated Moving Average Model
00:17:14
00:07:16
Decompose Time Series Data
00:08:09
Diffrentiation
00:05:41
How to identify Lags
00:05:38
Auto Arima
00:15:50
Forecast
00:02:33
Dummy Variables & Box Cox Transformation
00:02:20
Neural Network based Forecasting
00:09:42
Hyperparameter Tuning to increase accuracy
00:06:12
Conclusion
00:01:31