DataRobot Case Studies Harris Farm Markets Taps DataRobot for Demand Forecasting

Edit This Case Study Record

	Harris Farm Markets Taps DataRobot for Demand Forecasting DataRobot

Harris Farm Markets Taps DataRobot for Demand Forecasting

DataRobot

Technology Category	Analytics & Modeling - Predictive Analytics Platform as a Service (PaaS) - Data Management Platforms
Applicable Industries	Retail
Applicable Functions	Logistics & Transportation Warehouse & Inventory Management
Use Cases	Demand Planning & Forecasting Inventory Management
Services	Cloud Planning, Design & Implementation Services Data Science Services
Challenge	Harris Farm Markets, a grocery retailer in New South Wales, Australia, faced significant challenges in managing its perishable inventory due to unpredictable supply caused by wildfires and sudden spikes in demand due to COVID. With over two dozen stores and an expanding geographic footprint, the chain needed a way to consistently meet consumers’ demand for variety and freshness. The task of predicting demand for their 20,000 SKUs, including a subset of concurrent fresh produce running at 1200, was too vast for a manual approach. The company sought a solution that could provide accurate predictions with minimal labor on the part of the IT team. Read More
About Customer	Harris Farm Markets is a family-operated grocery retailer specializing in fruit and vegetable, gourmet meat, seafood, and bakery. With more than 25 physical stores, Harris Farm Markets aims to reconnect Aussies with the joy of food and bring the best that nature has to offer to their customers each day. The company operates in New South Wales, Australia, and has an expanding geographic footprint. It runs about 20,000 SKUs, or stock keeping units, with a subset of concurrent fresh produce running at 1200. The company sought a solution to better manage its perishable inventory and meet consumers’ demand for variety and freshness. Read More
Solution	Harris Farm Markets implemented DataRobot, an artificial intelligence and machine learning platform, to generate accurate demand predictions. The system took into account a wide range of data points, from seasonal impacts to customer numbers. DataRobot initially came online with around 100 AI models focused primarily on demand forecasting for fresh produce. Predictions from these models were fed into a custom-built buyers’ app that Harris Farm had already been using. The scoring pipeline was set to automatically run in a two-hour window every night, based on data from the previous day. A few months in, Harris Farm tweaked the model to target deployments by store, allowing the chain to turn off deployments for a store undergoing renovations, for example. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Predictive Analytics

Platform as a Service (PaaS) - Data Management Platforms

Applicable Industries

Retail

Applicable Functions

Logistics & Transportation

Warehouse & Inventory Management

Use Cases

Demand Planning & Forecasting

Inventory Management

Services

Cloud Planning, Design & Implementation Services

Data Science Services

Challenge

Harris Farm Markets, a grocery retailer in New South Wales, Australia, faced significant challenges in managing its perishable inventory due to unpredictable supply caused by wildfires and sudden spikes in demand due to COVID. With over two dozen stores and an expanding geographic footprint, the chain needed a way to consistently meet consumers’ demand for variety and freshness. The task of predicting demand for their 20,000 SKUs, including a subset of concurrent fresh produce running at 1200, was too vast for a manual approach. The company sought a solution that could provide accurate predictions with minimal labor on the part of the IT team.

About Customer

Harris Farm Markets is a family-operated grocery retailer specializing in fruit and vegetable, gourmet meat, seafood, and bakery. With more than 25 physical stores, Harris Farm Markets aims to reconnect Aussies with the joy of food and bring the best that nature has to offer to their customers each day. The company operates in New South Wales, Australia, and has an expanding geographic footprint. It runs about 20,000 SKUs, or stock keeping units, with a subset of concurrent fresh produce running at 1200. The company sought a solution to better manage its perishable inventory and meet consumers’ demand for variety and freshness.

Solution

Harris Farm Markets implemented DataRobot, an artificial intelligence and machine learning platform, to generate accurate demand predictions. The system took into account a wide range of data points, from seasonal impacts to customer numbers. DataRobot initially came online with around 100 AI models focused primarily on demand forecasting for fresh produce. Predictions from these models were fed into a custom-built buyers’ app that Harris Farm had already been using. The scoring pipeline was set to automatically run in a two-hour window every night, based on data from the previous day. A few months in, Harris Farm tweaked the model to target deployments by store, allowing the chain to turn off deployments for a store undergoing renovations, for example.

Impact #1	The implementation of DataRobot resulted in 400 deployments for demand and 30 for customer-number forecasts, using 25 individual models for hourly numbers and five clustered models for daily numbers.
Impact #2	The powerful analytic and predictive capability has helped Harris Farm cope with a steadily rising SKU count, something that had increased complexity in recent years.
Impact #3	Wastage has declined significantly, which has reduced costs and improved profits.

Impact #1

The implementation of DataRobot resulted in 400 deployments for demand and 30 for customer-number forecasts, using 25 individual models for hourly numbers and five clustered models for daily numbers.

Impact #2

The powerful analytic and predictive capability has helped Harris Farm cope with a steadily rising SKU count, something that had increased complexity in recent years.

Impact #3

Wastage has declined significantly, which has reduced costs and improved profits.

Benefit #1	Significant reduction in wastage, leading to cost savings and improved profits.
Benefit #2	Ability to manage a steadily rising SKU count, increasing operational efficiency.
Benefit #3	Increased capacity to manage perishable inventory, improving product availability and customer satisfaction.

Benefit #1

Significant reduction in wastage, leading to cost savings and improved profits.

Benefit #2

Ability to manage a steadily rising SKU count, increasing operational efficiency.

Benefit #3

Increased capacity to manage perishable inventory, improving product availability and customer satisfaction.

Download PDF Version

Overview

Harris Farm Markets Taps DataRobot for Demand Forecasting

Operational Impact

Quantitative Benefit