SlideShare a Scribd company logo

AI in retail

•Download as PPTX, PDF•
•
Subrat Panda, PhD
Subrat Panda, PhD

Fifth Elephant talk about AI in Retail - An introduction to using Computer Vision in Retail. Hasgeek Talk.

Related slideshows

Artificial intelligence in digital marketing
Artificial intelligence in digital marketingArtificial intelligence in digital marketing
Artificial intelligence in digital marketing
 
Generative AI at the edge.pdf
Generative AI at the edge.pdfGenerative AI at the edge.pdf
Generative AI at the edge.pdf
 
MG5705 AI in Marketing to share.pptx
MG5705 AI in Marketing to share.pptxMG5705 AI in Marketing to share.pptx
MG5705 AI in Marketing to share.pptx
 
1 of 14
+ AI in Retail Subrat Panda Fifth Elephant, Hasgeek Talk Principal Architect, Capillary Technologies, Co-Founder IDLI, https://www.facebook.com/groups/idliai/ 15th July, 2017
+ Agenda  What Capillary does ?  About me  Traditional application of AI in Retail  Neo-AI in Retail  Computer Vision in Retail  Building an AI application end to end  Questions
+ What Capillary does ?  Incubated in IIT Kharagpur  Successful SaaS Companies  CRM – Loyalty, Campaigns, Omni-Channel engagement  Helping our customers engage better with their customers through AI  A deep focus on AI based products for Omni-Channel Intelligent Customer Engagement
+ Brief Introduction about me  BTech ( 2002) , PhD (2009) – CSE, IIT Kharagpur  Synopsys (EDA), IBM (CPU), NVIDIA (GPU), Taro (Full Stack Engineer), Capillary (Principal Architect - AI)  Applying AI to Retail  Co-Founded IDLI (for social good) with Prof. Amit Sethi (IIT Bombay), Jacob Minz (Synopsys) and Biswa Gourav Singh (AMD)  https://www.facebook.com/groups/idliai/  Linked In - https://www.linkedin.com/in/subratpanda/  Facebook - https://www.facebook.com/subratpanda  Twitter - @subratpanda
+ Traditional Applications of AI in Retail  Customer Segmentation  Inventory Management  Recommender Systems  Campaign Management  Insights
+ Neo-AI in Retail  Enhanced Inventory Management – Takes care of other factors which could have been hard to decipher.  Enhanced Recommender Systems  Customer Engagement – Chatbots based interface (NorthFace – using IBM Watson)  Consumer Insights – Deep Understanding of Stores and Customers  Logistics and Delivery – Robots and Drones  Others – AI powered Gift Selection
+ Using Computer Vision in Retail Video analytics, derived through computer vision, helps retailers answer many critical questions, including:  How many shoppers entered the store?  What are my shoppers’ gender and age ranges?  Where do shoppers go in my store (and where do they not go)?  Where do shoppers stop and engage with fixtures or sales associates?  How long do they stay engaged?  Which are my most effective fixtures, and which ones are underperforming?  RetailNext integrates a variety of sensor technologies as part of its “technology stack” in building its industry-standard retail analytics platform.  Reference: https://retailnext.net/en/blog/computer-vision-sees-better- than-2020/
+ How we do this ?  How many shoppers entered the store? – People Counting  What are my shoppers’ gender and age ranges? – Demographic Analysis  Where do shoppers go in my store (and where do they not go)? - Heatmap  Where do shoppers stop and engage with fixtures or sales associates? – Shoppers Tracking  How long do they stay engaged? – Tracking and Identification  Which are my most effective fixtures, and which ones are underperforming? – Peel Off Counters  All of these can be solved using AI.
+ Computer Vision – The Sixth Sense in AI Retail  Affectiva, an MIT Lab spinoff that have analyzed over 5 million faces, enables retailers to use facial tracking to generate invaluable emotional insights the inform digital displays and in-store signage.  Sensing up to 7 human emotions (including anger, sadness, disgust, joy, surprise, fear and contempt) up to 20 different facial expressions, age range, ethnicity and gender, their recognition technology analyzes pixels in those regions to classify facial expressions and mapping them to associated emotion emojis.  Building customer segmentations based on computer vision data and sentiment analysis empowers retailers on a deeper level. It adds a layer of complex thinking to pass/fail decisions. It allows retailers to understand the dynamics of a living lab store environment. On a basic level it gives answers as to traffic patterns and dwell times, but on a more complex level it can drive true personalization. It can empower sales associates to serve as personal concierges to each customer.  Reference: https://www.linkedin.com/pulse/why-computer-vision-sixth-sense-retail-melissa- gonzalez
+ Computer Vision  Emotion plays a huge part in marketing and brand building  Technologies like AR, VR and 3D modeling are used to evoke those emotions.  Retailers can truly customize the consumer experience, advertise full product ranges more effectively, and also design more engaging and customer-friendly store layouts and displays to increase revenue  Popular in store #selfie marketing campaigns.  Reference : https://channels.theinnovationenterprise.com/articles/computer- vision-picturing-the-future-of-retail
+ Trax Trax offers three computer vision-based products:  Retail Execution: This product enables field reps of consumer packaged goods (CPG) companies and third-party auditors to capture shelf data with mobile phones and tablets and receive real-time reports on corrective actions to take in the store.  Shelf Intelligence Suite (by Trax and Nielsen): This product provides continuous and accurate retail measurement and analysis based on category shelf and point of sale data  Retail Watch: This product delivers real-time store monitoring analytics for retailers to reduce stockouts and improve planogram compliance.  Trax, a company that has developed a computer vision platform designed to provide data insights for consumer packaged goods companies and retailers, has received $64 million in funding.  Reference: http://www.vision-systems.com/articles/2017/06/computer-vision- company-enabling-retail-store-insights-receives-64-million-in-funding.html
+ NLP in Retail  Chatbots are ubiquitous  Customer engagement through contextual discussion  Different from normal FAQ based chatbots as context is lot relevant  Uses – preference elicitation, recommendation based on personal history, enables long contextual interactions.  LUIS from MS, WIT from FB, Watson’s Chatbot framework based in Bluemix.
+ Questions ?  Possibly answers also
+ References  https://www.techemergence.com/artificial-intelligence-retail-10- present-future-use-cases/  https://www.forbes.com/sites/kimberlywhitler/2016/12/01/how- artificial-intelligence-is-changing-the-retail-experience-for- consumers/#51422f6c1008

More Related Content

AI in retail

  • 1. + AI in Retail Subrat Panda Fifth Elephant, Hasgeek Talk Principal Architect, Capillary Technologies, Co-Founder IDLI, https://www.facebook.com/groups/idliai/ 15th July, 2017
  • 2. + Agenda  What Capillary does ?  About me  Traditional application of AI in Retail  Neo-AI in Retail  Computer Vision in Retail  Building an AI application end to end  Questions
  • 3. + What Capillary does ?  Incubated in IIT Kharagpur  Successful SaaS Companies  CRM – Loyalty, Campaigns, Omni-Channel engagement  Helping our customers engage better with their customers through AI  A deep focus on AI based products for Omni-Channel Intelligent Customer Engagement
  • 4. + Brief Introduction about me  BTech ( 2002) , PhD (2009) – CSE, IIT Kharagpur  Synopsys (EDA), IBM (CPU), NVIDIA (GPU), Taro (Full Stack Engineer), Capillary (Principal Architect - AI)  Applying AI to Retail  Co-Founded IDLI (for social good) with Prof. Amit Sethi (IIT Bombay), Jacob Minz (Synopsys) and Biswa Gourav Singh (AMD)  https://www.facebook.com/groups/idliai/  Linked In - https://www.linkedin.com/in/subratpanda/  Facebook - https://www.facebook.com/subratpanda  Twitter - @subratpanda
  • 5. + Traditional Applications of AI in Retail  Customer Segmentation  Inventory Management  Recommender Systems  Campaign Management  Insights
  • 6. + Neo-AI in Retail  Enhanced Inventory Management – Takes care of other factors which could have been hard to decipher.  Enhanced Recommender Systems  Customer Engagement – Chatbots based interface (NorthFace – using IBM Watson)  Consumer Insights – Deep Understanding of Stores and Customers  Logistics and Delivery – Robots and Drones  Others – AI powered Gift Selection
  • 7. + Using Computer Vision in Retail Video analytics, derived through computer vision, helps retailers answer many critical questions, including:  How many shoppers entered the store?  What are my shoppers’ gender and age ranges?  Where do shoppers go in my store (and where do they not go)?  Where do shoppers stop and engage with fixtures or sales associates?  How long do they stay engaged?  Which are my most effective fixtures, and which ones are underperforming?  RetailNext integrates a variety of sensor technologies as part of its “technology stack” in building its industry-standard retail analytics platform.  Reference: https://retailnext.net/en/blog/computer-vision-sees-better- than-2020/
  • 8. + How we do this ?  How many shoppers entered the store? – People Counting  What are my shoppers’ gender and age ranges? – Demographic Analysis  Where do shoppers go in my store (and where do they not go)? - Heatmap  Where do shoppers stop and engage with fixtures or sales associates? – Shoppers Tracking  How long do they stay engaged? – Tracking and Identification  Which are my most effective fixtures, and which ones are underperforming? – Peel Off Counters  All of these can be solved using AI.
  • 9. + Computer Vision – The Sixth Sense in AI Retail  Affectiva, an MIT Lab spinoff that have analyzed over 5 million faces, enables retailers to use facial tracking to generate invaluable emotional insights the inform digital displays and in-store signage.  Sensing up to 7 human emotions (including anger, sadness, disgust, joy, surprise, fear and contempt) up to 20 different facial expressions, age range, ethnicity and gender, their recognition technology analyzes pixels in those regions to classify facial expressions and mapping them to associated emotion emojis.  Building customer segmentations based on computer vision data and sentiment analysis empowers retailers on a deeper level. It adds a layer of complex thinking to pass/fail decisions. It allows retailers to understand the dynamics of a living lab store environment. On a basic level it gives answers as to traffic patterns and dwell times, but on a more complex level it can drive true personalization. It can empower sales associates to serve as personal concierges to each customer.  Reference: https://www.linkedin.com/pulse/why-computer-vision-sixth-sense-retail-melissa- gonzalez
  • 10. + Computer Vision  Emotion plays a huge part in marketing and brand building  Technologies like AR, VR and 3D modeling are used to evoke those emotions.  Retailers can truly customize the consumer experience, advertise full product ranges more effectively, and also design more engaging and customer-friendly store layouts and displays to increase revenue  Popular in store #selfie marketing campaigns.  Reference : https://channels.theinnovationenterprise.com/articles/computer- vision-picturing-the-future-of-retail
  • 11. + Trax Trax offers three computer vision-based products:  Retail Execution: This product enables field reps of consumer packaged goods (CPG) companies and third-party auditors to capture shelf data with mobile phones and tablets and receive real-time reports on corrective actions to take in the store.  Shelf Intelligence Suite (by Trax and Nielsen): This product provides continuous and accurate retail measurement and analysis based on category shelf and point of sale data  Retail Watch: This product delivers real-time store monitoring analytics for retailers to reduce stockouts and improve planogram compliance.  Trax, a company that has developed a computer vision platform designed to provide data insights for consumer packaged goods companies and retailers, has received $64 million in funding.  Reference: http://www.vision-systems.com/articles/2017/06/computer-vision- company-enabling-retail-store-insights-receives-64-million-in-funding.html
  • 12. + NLP in Retail  Chatbots are ubiquitous  Customer engagement through contextual discussion  Different from normal FAQ based chatbots as context is lot relevant  Uses – preference elicitation, recommendation based on personal history, enables long contextual interactions.  LUIS from MS, WIT from FB, Watson’s Chatbot framework based in Bluemix.