Skip to content

Analyzed historical monthly sales data of a company. Created multiple forecast models for two different products of a particular Wine Estate and recommended the optimum forecasting model to predict monthly sales for the next 12 months along with appropriate lower and upper confidence limits

Notifications You must be signed in to change notification settings

vaibhav-sing-bisht/Time-Series-Forecasting

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Time-Series-Forecasting

Analyzed historical monthly sales data of a company. Created multiple forecast models for two different products of a particular Wine Estate and recommended the optimum forecasting model to predict monthly sales for the next 12 months along with appropriate lower and upper confidence limits image

For Sparkling Dataset

image • The overall comparison of all the time-series forecast models are listed above table in accordance with increasing RMSE against test data or in order of decreasing accuracy.

• Triple exponential smoothing with alpha 0.4, Beta 0.1 and Gamma 0.2 performs to be the best model followed by manual SARIMA model. And lowest is performed by the Naïve model. image • The best of SARIMA, Triple Exponential Smoothing and Moving Average models are plotted above against the test data.

• The SARIMA and Triple Exponential Smoothing are found to be comparable in terms of performance and fitment with the test data.

For Rose Dataset

image • The overall comparison of all the time-series forecast models are listed below table 2.12 in accordance with increasing RMSE against test data or in order of decreasing accuracy.

• Triple exponential smoothing with alpha 0.1, Beta 0.2 and Gamma 0.1 performs to be the best model followed by 2 point moving average model. And lowest is performed by the Naïve model.

image

• The best of SARIMA, Triple Exponential Smoothing and Moving Average models are plotted above against the test data.

• 2 point trailing moving average is found to be having the best fitment against the test data, through with lag of 2 and falling short at times.

• Both SARIMA and Triple Exponential Smoothing are found a bit higher than actuals at any given point in time

Line Plot for 12 month forecast on Sparkling dataset

image image • The model forecast sale of 29508 units of sparkling wine in 12 months into future which is an average sale of 2459 units per month.

• The seasonal sale in December 1995 will hit a maximum of 6084 units before it drops to the lowest sale in January 1996 at 1215 units.

Line Plot for 12 month forecast on Rose dataset

image image

• The model forecast sale of 538 units of Rose wine in 12 months into future which is an average sale of 44 units per month.

• The seasonal sale in December 1995 will hit a maximum of 82 units before it drops to the lowest sale in January 1996 at 24 units.

About

Analyzed historical monthly sales data of a company. Created multiple forecast models for two different products of a particular Wine Estate and recommended the optimum forecasting model to predict monthly sales for the next 12 months along with appropriate lower and upper confidence limits

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages