Browse Prior Art Database

Method and System for Managing End to End Demand for Large Consumer Goods Manufacturer using ARIMA Disclosure Number: IPCOM000254249D
Publication Date: 2018-Jun-14
Document File: 6 page(s) / 211K

Publishing Venue

The Prior Art Database

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 35% of the total text.

Method and System for Managing End to End Demand for Large Consumer Goods Manufacturer using ARIMA

Companies today are investing a huge amount on tasks that could be fully/semi- automated. For a company that is manufacturing consumer goods one of the key challenge is to know how many units to manufacture based on the market demand since there are many factors in the play. Current sales forecasting and demand management systems lack steps to include various business scenarios into a demand management system, and are not automated end to end. There is a need for an end to end demand management framework to accurately forecast sales, plan production and inventory, allocate marketing budget, set sales targets, and plan support services. Disclosed is a method and system for managing end to end demand for large consumer goods manufacturer using Auto-Regressive Integrated Moving Average (ARIMA), wherein the method and system comprises exploratory data analysis (EDA) tool, modeling section and user dashboard. In accordance with the method and system, the EDA tool is exemplarily illustrated in figure 1 below. The EDA tool of the method and system runs thousands of iterations that helps a user understand the data being dealt with. Output from this section includes data summary and possible drivers of sale.

Figure 1

As illustrated in Figure 1, the EDA tool provides several options to upload dataset in a predetermined fashion such as import from text file, import from database and import from csv. The EDA tool asks the user to input sales data in the required granularity i.e. hourly, daily, weekly or monthly along with the additional/optional information as illustrated in Figure 2 below.

Figure 2

Upon the user clicking EDA button, following operations are executed, not necessarily in the same order. As illustrated in Figure 1 above, univariate analysis helps to understand quantity and quality of data (check for missing values), variance, outliers, inherent trends, and seasonality. Bivariate analysis helps to check correlation between dependent and independent variables. Treatment of missing values provides several treatment options to impute missing values, including but not limited to, drop, replace with mean, replace with mode, replace with zero, and retain. “Replace with mean” is by default selected. Treatment of outliers provides several treatment options to handle outliers including drop, truncate with mean ± N variance, replace with mean, and retain. Default is chosen as truncate with mean ± 2 variance. Transformation of independent variables is done to increase the correlation with respect to the dependent variable i.e. sales. The EDA tool uses an automation logic to run several thousand iterations of transformation trying to maximize the correlation between dependent variable and transformed independent variable. In an exemplary scenario, the method and system runs four types of transformation, including lag, allocation, adstock and smoothing. If...