Dataiku Case Studies MandM Direct: Managing Models at Scale with Dataiku + GCP

Edit This Case Study Record

	MandM Direct: Managing Models at Scale with Dataiku + GCP Dataiku

MandM Direct: Managing Models at Scale with Dataiku + GCP

Dataiku

Technology Category	Analytics & Modeling - Machine Learning Platform as a Service (PaaS) - Data Management Platforms
Applicable Industries	Retail
Applicable Functions	Sales & Marketing Business Operation
Use Cases	Predictive Maintenance Inventory Management Supply Chain Visibility
Services	Cloud Planning, Design & Implementation Services Data Science Services
Challenge	MandM Direct, one of the largest online retailers in the United Kingdom, faced a significant challenge as they grew rapidly. With over 3.5 million active customers and seven dedicated local market websites across Europe, the company delivers more than 300 brands annually to 25+ countries worldwide. Their accelerated growth meant more customers and, therefore more data, which magnified some of their challenges and pushed them to find more scalable solutions. The two main challenges were getting all the available data out of silos and into a unified, analytics-ready environment and scaling out AI deployment in a traceable, transparent, and collaborative manner. Initially, the company's first machine learning models were written in Python (.py files) and run on the data scientist’s local machine. However, as the number of models in production increased, the team quickly realized the burden involved in maintaining models. Read More
About Customer	MandM Direct is one of the largest online retailers in the United Kingdom with over 3.5 million active customers and seven dedicated local market websites across Europe. The company delivers more than 300 brands annually to 25+ countries worldwide. In 2020, they experienced rapid growth which resulted in an increase in customers and data. This growth magnified some of their challenges and pushed them to find more scalable solutions. The core data team is made up of four people (two data scientists, one senior analyst, and one data analyst), but they extend their reach by leveraging a hub and spoke model for their data center of excellence, meaning they work with analysts embedded across the business lines to scale their efforts. Read More
Solution	To tackle their challenges, MandM Direct turned to the powerful combination of Dataiku and Google Cloud Platform (GCP). With Google BigQuery’s fully-managed, serverless data warehouse, MandM could break the data silos and democratize data access across teams. At the same time, thanks to Dataiku’s visual and collaborative interface for data pipelining, data preparation, model training, and MLOps, MandM could also easily scale out their models in production without failure or interruptions in a transparent and traceable way. MandM now has hundreds of live models doing everything from scoring customer propensity to generating pricing models, all with visibility into model performance metrics, clear separation of design and production environments, and many more MLOps capabilities built into the platform. Teams can now easily push-down and offload computations for both data preparation and machine learning to GCP. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Machine Learning

Platform as a Service (PaaS) - Data Management Platforms

Applicable Industries

Retail

Applicable Functions

Sales & Marketing

Business Operation

Use Cases

Predictive Maintenance

Inventory Management

Supply Chain Visibility

Services

Cloud Planning, Design & Implementation Services

Data Science Services

Challenge

MandM Direct, one of the largest online retailers in the United Kingdom, faced a significant challenge as they grew rapidly. With over 3.5 million active customers and seven dedicated local market websites across Europe, the company delivers more than 300 brands annually to 25+ countries worldwide. Their accelerated growth meant more customers and, therefore more data, which magnified some of their challenges and pushed them to find more scalable solutions. The two main challenges were getting all the available data out of silos and into a unified, analytics-ready environment and scaling out AI deployment in a traceable, transparent, and collaborative manner. Initially, the company's first machine learning models were written in Python (.py files) and run on the data scientist’s local machine. However, as the number of models in production increased, the team quickly realized the burden involved in maintaining models.

About Customer

MandM Direct is one of the largest online retailers in the United Kingdom with over 3.5 million active customers and seven dedicated local market websites across Europe. The company delivers more than 300 brands annually to 25+ countries worldwide. In 2020, they experienced rapid growth which resulted in an increase in customers and data. This growth magnified some of their challenges and pushed them to find more scalable solutions. The core data team is made up of four people (two data scientists, one senior analyst, and one data analyst), but they extend their reach by leveraging a hub and spoke model for their data center of excellence, meaning they work with analysts embedded across the business lines to scale their efforts.

Solution

To tackle their challenges, MandM Direct turned to the powerful combination of Dataiku and Google Cloud Platform (GCP). With Google BigQuery’s fully-managed, serverless data warehouse, MandM could break the data silos and democratize data access across teams. At the same time, thanks to Dataiku’s visual and collaborative interface for data pipelining, data preparation, model training, and MLOps, MandM could also easily scale out their models in production without failure or interruptions in a transparent and traceable way. MandM now has hundreds of live models doing everything from scoring customer propensity to generating pricing models, all with visibility into model performance metrics, clear separation of design and production environments, and many more MLOps capabilities built into the platform. Teams can now easily push-down and offload computations for both data preparation and machine learning to GCP.

Impact #1	MandM Direct was able to break the data silos and democratize data access across teams.
Impact #2	The company could easily scale out their models in production without failure or interruptions in a transparent and traceable way.
Impact #3	MandM now has hundreds of live models doing everything from scoring customer propensity to generating pricing models, all with visibility into model performance metrics, clear separation of design and production environments, and many more MLOps capabilities built into the platform.

Impact #1

MandM Direct was able to break the data silos and democratize data access across teams.

Impact #2

The company could easily scale out their models in production without failure or interruptions in a transparent and traceable way.

Impact #3

MandM now has hundreds of live models doing everything from scoring customer propensity to generating pricing models, all with visibility into model performance metrics, clear separation of design and production environments, and many more MLOps capabilities built into the platform.

Benefit #1	MandM Direct operationalizes 10x more models versus a code-only approach.
Benefit #2	The company now has hundreds of live models in production.
Benefit #3	The data team is now able to deliver a variety of business solutions on business problems from adtech to customer lifetime value.

Benefit #1

MandM Direct operationalizes 10x more models versus a code-only approach.

Benefit #2

The company now has hundreds of live models in production.

Benefit #3

The data team is now able to deliver a variety of business solutions on business problems from adtech to customer lifetime value.

Download PDF Version

Overview

MandM Direct: Managing Models at Scale with Dataiku + GCP

Operational Impact

Quantitative Benefit