How Mahindra Logistics’ focus on tech led to increased inventory accuracy across its warehouses

In a time when customer expectations around order fulfilment (time as well as accuracy) are increasing, it is only obvious to invest in technology that makes managing your inventory and warehouse easier. It becomes important and rather basic, to track every unit down to the lowest level of detail for improved order fulfilment and inventory accuracy. You should neither over-stock warehouses (the capital can be invested in some other part of the business), nor should there be situations of stockout due to inaccuracy (which can lead to shipping delays and irate customers). The goal is to hit that ‘sweet spot’ to ensure that you have what you need to meet your customers’ demands without overspending on excess inventory and associated storage costs. Good inventory management will help you get there, and good inventory management starts with inventory accuracy.

An organisation should invest in technology backed solutions that result in improved inventory accuracy and visibility. The process of counting and monitoring inventory should be simple, allowing frequent inventory count. Moreover, the inventory level should always reflect actual physical inventory stored in the warehouse at any particular time.

Mahindra Logistics Limited (MLL) – the homegrown 3rd party logistics (3PL) service provider, specialising in supply chain management – serves over 400+ corporate customers across various industries, and pursues an ‘asset-light’ business model, providing customised and technology-enabled solutions that span across their supply chain operations.

It is not unknown that MLL also engages in warehouse services for its customers, which includes inventory control and storage management. It manages over 17 million square feet of warehousing space at multiple locations across India, which are a mix of built-to-suit, dedicated and multi-user warehouses. 

Their modern warehouses handle huge quantities of cargo each day and execute processes like counting, sorting, checking etc., for both incoming as well as outgoing cargo. Imagine thousands of packages of various sizes moving through the warehouse each day. Now imagine the number of workers it takes (at multiple levels in the hierarchy) to processes each of those packages. And further, think of how much time a single worker gives to match each package to its invoice/DC and then perform safety and quality checks – multiply that by at least a figure in the hundreds.

Even the thought of all this is tiring.

Because of their repetitive nature, the manually performed counting and checking tasks are prone to errors, which leads to inconsistencies in inventory counts and identifying of damages. Supervisors are performing repetitive tasks which are also subject to fatigue and inaccuracies.

To resolve this problem, MLL put the onus on Jidoka Technologies to create an AI-based cargo counting system that can record case counts and damages, and perform invoice matching for all incoming and outgoing shipments, while ensuring traceability to invoice/DC in the WMS systems.

Jidoka had the responsibility of creating a cognitive system for 100% digital inspection and visibility of shipments at the time of receipt as well as dispatch. The said solution had to keep in view, count, barcode/QR code detection, SKU type detection, and box damage condition and detection, while ensuring the best fit in the pallet system. They started by interacting with the workers and supervisors to understand what exactly was expected from the solution they were assigned to design.

Jidoka developed a Machine Vision based hardware setup and the software was integrated with Programmable Controllers (PLCs). These processors enabled the running of automation programs and played a key role in the automation of the warehouses. 

They set up a non-intrusive camera for inspection and AI-driven models were leveraged to mimic human counting, thereby providing consistency and efficiency in repetitive tasks. The solution was made mobile across docks. This was first piloted at the distribution warehouse in South India. The solution evolved as the users started to see the system in action both from automation and software perspectives.  

With the tech solution developed exclusively for MLL, more than 99% accuracy was achieved in package counting and inspection at the inbound as well as outbound stage. The supervisor’s productivity was increased by 50% with zero supervision on counting and quality checks, providing up to 20% savings on labor costs. Its non-intrusive nature allowed the task performance at or better than human speeds Automated reconciliation against WMS/ERP system was established. The solution was mobile and deployable. Traceability was achieved.

MLL recognised that focusing on warehouse accuracy lead to improved inventory management and reduced overhead costs. This ultimately meant that the resources spent on implementation of the system to improve warehouse accuracy was well worth the investment. The solution designed by Jidoka resulted in improved inventory visibility, reduced overhead costs, minimum idle time, and increased customer satisfaction.

Leave a Reply

Your email address will not be published. Required fields are marked *