India's largest platform for AI & Analytics leaders, professionals & aspirants

Sign in

India's largest platform for AI & Analytics leaders, professionals & aspirants

Featured Article:

Author: Shrinath Bhat, Senior Data Scientist, AB InBev

Supply Chain of Future (SCoF) Analytics team’s vision, which is a part of Growth Analytics Centre (GAC): the global analytics hub for Ab-InBev, is to create value via adoption of cutting-edge practices in Supply Chain domain with a series of digital transformations and advanced analytics methodologies to keep the organizations focused on high-value tasks. We are transforming our company’s operations which has 200+ Breweries, 600+ Distribution Centers, 1000+ SKUs and 60+ Verticals. Overall, $25 B+ Industrial and Logistics Operating cost, where $5Bn+ is incurred in Logistics cost, $2.1Bn+ of expenses in Storage, $4.8Bn+ of inventory cost at any given time, $100Mn+ of Obsolescence and $1.7Bn+ of Out of Stock is recorded historically.

Inventory Re-Deployment Project

What is Inventory Re-deployment?

Before we jump on to understanding the redeployment process let’s revisit some basics.

There are three important constituents in any supply chain network. They are

Inventory deployment is the movement of finished goods from locations “higher” in the supply network (like Brewery) to locations “lower” in the supply network (like Distribution Centers).

Inventory re-deployment is the movement of finished goods between Distribution Centers.

Below diagram explains the same:

Why do we need to redeploy?

We need redeployment to manage out of stock and obsolescence because of high demand volatility and ineffective demand planning.

The goal of the project is to improve stock availability to meet customer demand and service levels by optimizing the re-deployment of stock to maintain a balanced inventory across all the depots in a country

Key Issue in Logistics and Supply Chain:

Why is there a need to relook at the Re-deployment process?
There was a question asked by Logistics Capabilities Partners, “Is there a process to check re-deployment opportunities for the main risks of Obsolescence and Out of Stock with a clear view on cost implications?”

Answer to the question is no!

In the previous process:

We are hence trying to solve the above issues in the optimized process:

Data Landscape

There are various datafiles used in for the analytical data set preparation at DC-SKU (Distribution Center-Stock Keeping Unit) level which come from various data sources like SAP, Vertica, Tableau dashboard etc. and which can be majorly categorized into the following categories:

With information on the opening stock, planned in volume, in-transit volume, planned production, average demand forecast, customer orders and re-order point

With information on the location of the DCs, Trip cost involved for the redeployment etc.

With information on the MACO without VLC, unit of measurement, stock age, out of stock etc.

The above-mentioned raw data is further preprocessed and transformed into the analytical data set.

There are 5 inputs to the optimization model:

Business Rules and Assumptions

There are various business rules and assumptions which are also an input to the optimization model as constraints. These rules and assumptions vary across countries and zones.

The following are a few of the rules and assumptions which need to be followed:

Optimization Model Solution Design

Inventory Redeployment Product

Key elements of Product framework are:

Data ecosystem is built with the data being extracted automatically from the data sources like SAP, Data Lake, Vertica etc.

Solution ecosystem is built with AI-powered seamless integration of the redeployment model, it’s performance report, root cause analysis and configurable scheduler.

User ecosystem is built with manual automated trigger, integrated downstream platform and experiments tracking on the collaboration platform.


Imbalance of stock availability across depots is one of the major issues in supply chain and for solving it Inventory optimization model, an AI-powered linear optimization algorithm which recommends cost-optimized stock movements driven by out-of-stock and obsolescence has been developed, automating the earlier manual and inefficient processes. This solution will be implemented in 6 zones across 15 countries and has a potential opportunity of around $30Mn EBIDTA savings.

India’s largest platform for AI & Analytics leaders, professionals & aspirants

3AI is India’s largest platform for AI & Analytics leaders, professionals & aspirants and a confluence of leading and marquee AI & Analytics leaders, experts, influencers & practitioners on one platform.

3AI platform enables leaders to engage with students and working professionals with 1:1 mentorship for competency augmentation and career enhancement opportunities through guided learning, contextualized interventions, focused knowledge sessions & conclaves, internship & placement assistance in AI & Analytics sphere.

3AI works closely with several academic institutions, enterprises, learning academies, startups, industry consortia to accelerate the growth of AI & Analytics industry and provide comprehensive suite of engage, learn & scale engagements and interventions to our members. 3AI platform have 16000+ active members from students & working professionals community, 500+ AI & Analytics thought leaders & mentors and an active outreach & engagement with 430+ enterprises & 125+ academic institutions.