PREDICTIVE ANALYTICS AT SCALE IN RETAIL

bussines-dataiku

In the booming retail business, big data is poised in the coming years to open up huge opportunities in the way stores (both physical and online) fundamentally operate and serve customers.

Just look at the way giants of the digital age (Google, Apple, Facebook, and Amazon -GAFA) have affected the retail space already with data-first business models.

Given the incredibly small margins in retail, efficiency improvements anywhere – from tighter supply chain management to more targeted marketing campaigns – can make a big difference to a retail business of any size.

TRANSFORM BUSINESS WITH PREDICTIVE ANALYTICS

Making data-driven decisions is no longer about learning from the past; it means making changes to the business constantly based on realtime input from all data sources across the organization. Making predictions and applying machine learning is based on traditional data but also on new and innovative sources like connected Internet of Things (IoT) devices and sensors or, going a step further with deep learning, unstructured data from things like static images or cameras monitoring stock in warehouses. Consumers can be fickle, so being able to accurately anticipate what they will do next and quickly react is what puts the most innovative and successful retailers above the rest:

SILOED, STATIC CUSTOMER VIEWS

Many retailers still struggle with siloed data – transaction data lives apart from web logs which in turn is separate from CRM data, etc.

SILOED, STATIC CUSTOMER VIEWS

Many retailers still struggle with siloed data – transaction data lives apart from web logs which in turn is separate from CRM data, etc.

run More accurate and targeted churn prediction

Robust fraud detection systems Robust fraud detection systems

More effectiveMore effective marketing campaigns due to more advanced customer segmentation

Better customer service Better customer service

TIME CONSUMING VENDOR & SUPPLY CHAIN MANAGEMENT

Supply chains are already driven by numbers and analytics, but retailers have been slow to embrace the power of realtime analytics and harnessing huge, unstructured data sets.

AUTOMATION AND PREDICTION FOR FASTER, MORE ACCURATE MANAGEMENT

Combine structured and unstructured data in real time for things like more accurate forecasts or automatic reordering.

lupa Optimized pricing strategies

statsMore efficient inventory management based on real time data and behavior

ANALYSIS BASED ON HISTORICAL DATA

Looking back at shoppers’ past activity often isn’t a good indication of what they will do next.

PREDICTION AND MACHINE LEARNING IN REAL TIME

Instead, real time prediction based off of current trends and behaviors from all sources of data is the key.

anticipating-what-a-customerAnticipating what a customer will do next

agile-businessA more agile business based on up-to-theminute signals

customer-behavior The ability to adapt automatically with customer behavior

ONE-TIME DATA PROJECTS

Completing one-off data projects that aren’t reproducible is frustrating and inefficient.

AUTOMATED, SCALABLE, AND REPRODUCIBLE DATA INITIATIVES

The best data teams in retail focus on putting a data project into production that is completely automated and scalable.

 More efficient team that can scale as the company grows

with-reproducible-workflows With reproducible workflows, team can work on more projects

BUILD SUCCESSFUL DATA PROJECTS AT SCALE

run Detecting Potential Churners in Retail with 77% Accuracy

In order to counter churn, Showroomprive (a leading e-commerce player in Europe with more than 20 million members) previously used static rules common to all customers to trigger marketing actions. They were not doing any prior qualification to determine the value of each individual client before triggering marketing actions.

Showroomprive chose Dataiku Data Science Studio (DSS) to develop a robust solution that predicts whether or not a buyer will return to the website to make a purchase:

document Maximizing Sales and Profits with Optimized Inventory Management

A large brick-and-mortar retail chain was losing money due to lack of real-time order management and losing time placing orders on a large inventory. When items went out of stock, it was inefficient and time consuming to get them restocked quickly.

This retail chain used Dataiku Data Science Studio (DSS) to incorporate data from a large variety of sources to completely optimize their supply chain and automate it when possible:

PREDICTIVE ANALYTICS AT SCALE IN RETAIL

Automated the integration Automated the integration and enrichment of a variety of data sources (including customer data, order and delivery data, web logs, etc.).

features Created more than 690 features derived from this data depending on variables like clicks on sales, orders, customer profile, etc.

Tested multiple machine Tested multiple machine learning algorithms to achieve the best predictive model.

PREDICTIVE ANALYTICS AT SCALE IN RETAIL

Incorporated geo-socialIncorporated geo-social data to predict big events in the area likely to result in out-of-stock items and stock additional, specific items when called for.

Automated productAutomated product sourcing thanks to a real-time view of demand, sourcing, and sales combined with data on lead time and weather in the area that may affect suppliers.

FasterFaster order picking by using data from multiple sources (like historical picking times and warehouse layouts) to ship and fulfill orders faster.

The most successful retail companies worldwide are able to efficiently leverage all of the data at their fingertips by following set processes to see data projects through from start to finish. They also ensure those data projects are reproducible and scalable so the data team is constantly able to work on new projects vs. maintaining old ones. This is as easy as following the seven fundamental steps to completing a data project

steps

©2017 Dataiku, Inc. | www.dataiku.com | contact@dataiku.com | @dataiku | Created by: EM360