retail personalization

27
Enabling Personal and Relevant Engagement ShiSh Worldwide Director, Analytics & IoT, Retail Sector, Microsoft Corp Machine Learning & Retail

Upload: shish-shridhar

Post on 09-Jan-2017

559 views

Category:

Retail


0 download

TRANSCRIPT

Page 1: Retail personalization

Enabling Personal and Relevant Engagement

ShiShWorldwide Director, Analytics & IoT, Retail Sector,

Microsoft Corp

Machine Learning & Retail

Page 2: Retail personalization

What product is Joe most likely to buy?

Page 3: Retail personalization

Will Sarah come back to shop with us next month?

Page 4: Retail personalization

What advertising would be most effective to get Johan’s attention?

Page 5: Retail personalization

Listening to the voice of the customer

1995 1996 1997 1998 1999 2000 2001 200205

1015202530

Sales Forecast in 1999

Film Cameras Digital Cameras

1995 1996 1997 1998 1999 2000 2001 200202468

101214161820

What Really Happened

Film Cameras Digital Cameras

Page 6: Retail personalization

Retail has a multitude of devices that

generate petabytes of potential insights

Monitoring and mining social media data

enables retailers to enhance customer

insights

Open data sources and internal sources enable retailers to better understand

customers

Democratization of data

Page 7: Retail personalization

Cortana Analytics

Information Management

Big Data Stores

Machine Learning & Analytics

Visualization

Democratization of Tools

Page 8: Retail personalization
Page 9: Retail personalization

Machine LearningData

ProgramOutput

Data

Program

Data

OutputProgram

Page 10: Retail personalization

Put customers first with technology that learns, predicts, and engages

at a personal level

» Predict what customers want before they tell you

» Engage with customers at the right time, right place with the right offers

» Personalize the customer experience across channels

» Improve loyalty, "share of wallet" through hyper-local assortments and inventory

Page 11: Retail personalization

Foodservice retailer built brand loyalty with a cloud-based mobile app

Challenge • Improve

relationships with customers.

• Build upon a successful brand app to reach more customers.

• Generate upsales and cross-sales.

Strategy• Added an analysis

and insights system based on Microsoft Azure.

• Gathered data on customers’ behaviors and preferences through their app use.

Results• Expanded app use to millions

of customers in five countries.

• Enabled personal, relevant, contextual content that adds value for the users.

• Improved customer loyalty.

Page 12: Retail personalization

Demo

Page 13: Retail personalization
Page 14: Retail personalization

Key Driver Analytics

Page 15: Retail personalization

Regional Retail Store Beverage Sales Overview – 1

15

Sales for Northwest Territory retailer

Seattle is facing sales problems

Problem: Seattle is not selling to forecast

1

2

Page 16: Retail personalization

16

Seattle soft drink segment sales fell below expectation

When we drill down to Seattle, we can see a problem in soft drinks

Click and see further details of Seattle sales

Regional Retail Store Beverage Sales Overview – 2

1

2

Page 17: Retail personalization

17

Powerful Solution with Advanced Analytics• Question: OK, now we know we have a problem but how can we solve it? • Answer: “With advanced analytics!”

Sales driver analysis– build a model that explains

what drives sales

Sales delta analysis – use the model to see

problems

3. How can we fix sales?– apply the model to fix the

problems

21 3

Page 18: Retail personalization

18

Start with internal transaction and marketing data to get part of the picture

Sales Driver Analysis – 1

25.6% variations explained

Internal transaction and marketing data include variables as:- Stock Up- Price Elasticity- Radio

Advertising- TV Advertising- SKU presence

Transaction dataset in AML

experiment

12

3

Page 19: Retail personalization

19

Add external data to and now the model accuracy is improved Sales Driver Analysis – 2

Variations explained

improves to near 50%

External weather, demographic, and competitor data include variables as:- Temperature- Precipitation- Household

size- Annual Income- Competitor

Price Gap

Transaction dataset in AML

experiment

External dataset enters the

model in AML experiment

2

13

4

Page 20: Retail personalization

20

With IoT, research, and online activity data, we can build sales models of unprecedented power for end users

Sales Driver Analysis – 3

IoT dataset enters the

model in AML experiment

Variations explained

improves to 89%

New IoT, research and online activity data include variables as:- Survey research- Web traffic- Social media

traffic- Mobile traffic- Store traffic- Shelf traffic

Transaction dataset in AML

experiment

External dataset enters the

model in AML experiment

2

41

35

Page 21: Retail personalization

21

Analyze impact of key sales drivers over the last one monthSales Driver Impact - 1

Monthly ∆ by sales driver

Let’s first zero in on the sales impact of price gaps, as they are the biggest problem

Competitor price gap caused 7,598 less units sold than previous month

Click one of the controllable variables to see what would happen if we take some actions

21

34

Page 22: Retail personalization

22

What would be the impact on sales if I adjust my pricing?Sales Driver Impact - 2

See the impact on physical sales if we reduce the price gap by different levelsSee the impact on profit if we reduce the price gap by different levels. When it is reduced by 15%, we would be able to achieve 4.5K incremental profit.

Select competitor price gap as it is a controllable variable

It would be recommended to decrease the competitor price gap

2

1

3

4

Page 23: Retail personalization

23

What would be the impact on sales if I adjust my pricing?Sales Driver Impact - 2

See the impact on physical sales if we increase social media engagement by different levelsSee the impact on profit if we increase social media engagement by different levels. When it is increased by 20%, we would be able to achieve 12.6K incremental profit.

Select Social Media Engagement as it is a controllable variable

It would be recommended to increase social media engagement

2

1

3

4

Page 24: Retail personalization

24

What would be the impact on sales if I adjust my pricing?Sales Driver Impact - 2

See the impact on physical sales if we increase advertising by different levels

See the impact on profit if we increase advertising by different levels. When it is increased by 20%, we would be able to achieve 7.1K incremental profit.

Select Own Brand Advertising as it is a controllable variable

It would be recommended to increase our own brand advertising

2

1

3

4

Page 25: Retail personalization

25

IoT Driving Insights, Decisions & EngagementIoT in retail could have an economic impact of $410 billion to $1.2 trillion per year in 2025

Page 26: Retail personalization

26

Page 27: Retail personalization