Each project comes with 2-5 hours of micro-videos explaining the solution.
Code & Dataset
Get access to 50+ solved projects with iPython notebooks and datasets.
Add project experience to your Linkedin/Github profiles.
Understanding the problem statement
Importing the dataset from amazon AWS
Single period forecasting and multiple period forecasting
Univariate time series forecasting and multivariate time series forecasting
Seasonality, Trend, and Cyclicity
Moving average as a method of smoothing out the dataset
Performing basic EDA
Visualizing a time series using graph
Timestamping the necessary columns
How to decompose a time series
Rolling mean or moving average
Standardization and Normalization of the time series
Visualizing standardized data using barplot
What is upsampling and downsampling
Understanding the relationship between different variables using Univariate and Multivariate analusis
AR, MA, ARIMA, ARMA, UCM and Exponential smoothing model
How to implement ARIMA model
Defining the evaluation metrics
Plotting the error terms or residuals
Making predictions using the ARIMA model
Plotting the model results
Different methods to make the predictions better
Time series forecasting has been one of the important area in data science, it is important to predict a variable associated with time elements such as sales, demand, revenue, profit etc. For logistic and supply chain companies, they need to know the exact inventory they need to stock for that they need to predict the demand for future.
Similarly, people in sales and marketing need to know how much order the customers are going to place so that they can manage their staff. Telecom companies should know how much manpower they need to prepare so that they can handle peak hour traffic etc. In various businesses, at least 5-10 areas where the variable of interest is associated with the time element.
Let’s look at few examples where we can apply various time series forecasting techniques.