Demand Planning

Assembly Line

How Walmart Uses Apache Kafka for Real-Time Replenishment at Scale

Date:

Topics: Inventory Optimization, Demand Planning

Organizations: Walmart, Confluent

Real-time inventory planning has become a must for Walmart in the face of rapidly changing buyer behaviors and expectations. But real-time inventory is only half of the equation. The other half is real-time replenishment, which at a high level, we define as the way we can fulfill the inventory demand at every physical node in the supply chain network. As soon as inventory gets below a certain threshold, and based on many other supply chain parameters like sales forecast, safety stock, current availability of the item at node and its parents, we need to automatically replenish that item in a way that optimizes resources and increases customer satisfaction.

On any given day, Walmart’s real-time replenishment system processes more than tens of billions of messages from close to 100 million SKUs in less than three hours. We leverage an array of processors to generate an order plan for the entire network of Walmart stores with great accuracy and at high throughputs of 85GB messages/min. While doing so, it also ensures there is no data loss through event tracking and necessary replays and retries.

Read more at Confluent Blog

Production Planning Template for Excel (Free Download)

Date:

Topics: Demand Planning

Organizations: Anvyl

A production plan is a guide that outlines every step involved in the production of a good. With production planning, the production process is more organized and efficient, and there is less of a risk of missing an important step that stops or slows down production. These plans help optimize the manufacturing process, which makes the design, production, and delivery of goods much easier to plan out.

An Excel template can work as a jumping-off point, allowing your business to build around your own goals and needs without starting from scratch. Keep in mind that a template should be flexible enough to allow for personalization while also being rigid enough that you don’t miss vital steps. The Anvyl production planning template was built with this mentality: to help manufacturers improve their processes and create a better production planning experience with a unique, customizable approach.

Read more at Anvyl Blog

Price optimization notebook for apparel retail using Google Vertex AI

Date:

Authors: Volodymyr Koliadin, Ilya Katsov

Topics: Demand Planning

Vertical: Apparel

Organizations: Google

One of the key requirements of a price optimization system is an accurate forecasting model to quickly simulate demand response to price changes. Historically, developing a Machine Learning forecast model required a long timeline with heavy involvement from skilled specialists in data engineering, data science, and MLOps. The teams needed to perform a variety of tasks in feature engineering, model architecture selection, hyperparameter optimization, and then manage and monitor deployed models.

Vertex AI Forecast provides advanced AutoML workflow for time series forecasting which helps dramatically reduce the engineering and research effort required to develop accurate forecasting models. The service easily scales up to large datasets with over 100 million rows and 1000 columns, covering years of data for thousands of products with hundreds of possible demand drivers. Most importantly it produces highly accurate forecasts. The model scored in the top 2.5% of submissions in M5, the most recent global forecasting competition which used data from Walmart.

Read more at Google Cloud Blog

The evolution of Amazon’s inventory planning system

Date:

Topics: demand planning, operations research, E-commerce, glocalization

Organizations: Amazon

Forecasting models developed by Amazon’s Supply Chain Optimization Technologies organization predict the demand for every product. Buying systems determine the right level of product to purchase from different suppliers, while large-scale placement systems determine the optimal location for products across the hundreds of facilities belonging to Amazon’s global fulfillment network.

“In 2016, Amazon’s supply chain network was designed for scenarios where inventory from any fulfillment center could be shipped to any customer to meet a two-day promise,” said Salal Humair, senior principal research scientist at Amazon who has been with the company for seven years. This design was inadequate for the new world in which Amazon was operating; one shaped by what Humair calls the “globalization-localization imperative.”

A new multi-echelon inventory system developed by SCOT (a project whose roots stretch back to 2016) is a significant break from the past. The heart of the model is a multi-product, multi-fulfillment center, capacity-constrained model for optimizing inventory levels for multiple delivery speeds, under a dynamic fulfillment policy. The framework then uses a Lagrangian-type decomposition framework to control and optimize inventory levels across Amazon’s network in near real-time.

Broadly speaking, decomposition is a mathematical technique that breaks a large, complex problem up into smaller and simpler ones. Each of these problems is then solved in parallel or sequentially. The Lagrangian method of decomposition factors complicated constraints into the solution, while providing a ‘cost’ for violating these constraints. This cost makes the problem easier to solve by providing an upper bound to the maximization problem, which is critical when planning for inventory levels at Amazon’s scale.

Read more at Amazon Science

The history of Amazon’s forecasting algorithm

Date:

Topics: demand planning, random forest, natural language processing

Organizations: Amazon

Historical patterns can be leveraged to make decisions on inventory levels for products with predictable consumption patterns — think household staples like laundry detergent or trash bags. However, most products exhibit a variability in demand due to factors that are beyond Amazon’s control.

Today, Amazon’s forecasting team has drawn on advances in fields like deep learning, image recognition and natural language processing to develop a forecasting model that makes accurate decisions across diverse product categories. Arriving at this unified forecasting model hasn’t been the result of one “eureka” moment. Rather, it has been a decade-plus long journey.

Read more at Amazon Science

How Instacart fixed its A.I. and keeps up with the coronavirus pandemic

Date:

Author: @JonathanVanian

Topics: COVID-19, demand planning, machine learning

Organizations: Instacart

Like many companies, online grocery delivery service Instacart has spent the past few months overhauling its machine-learning models because the coronavirus pandemic has drastically changed how customers behave.

Starting in mid-March, Instacart’s all-important technology for predicting whether certain products would be available at specific stores became increasingly inaccurate. The accuracy of a metric used to evaluate how many items are found at a store dropped to 61% from 93%, tipping off the Instacart engineers that they needed to re-train their machine learning model that predicts an item’s availability at a store. After all, customers could get annoyed being told one thing—the item that they wanted was available—when in fact it wasn’t, resulting in products never being delivered. ‘A shock to the system’ is how Instacart’s machine learning director Sharath Rao described the problem to Fortune.

Read more at Fortune (Paid)

The algorithms big companies use to manage their supply chains don’t work during pandemics

Date:

Author: Nicole Wetsman

Topics: COVID-19, demand planning

Organizations: Alloy, Walmart

Even during a pandemic, Walmart’s supply chain managers have to make sure stores and warehouses are stocked with the things customers want and need. COVID-19, though, has thrown off the digital program that helps them predict how many diapers and garden hoses they need to keep on the shelves.

Normally, the system can reliably analyze things like inventory levels, historical purchasing trends, and discounts to recommend how much of a product to order. During the worldwide disruption caused by the COVID-19 pandemic, the program’s recommendations are changing more frequently. “It’s become more dynamic, and the frequency we’re looking at it has increased,” a Walmart supply chain manager, who asked not to be named because he didn’t have permission to speak to the media, told The Verge.

Read more at The Verge