Mall Intelligence Network (MIN)

Mall Intelligence Network (MIN) is the term first coined by retail futurist, author & data scientist Mr. Yogesh Huja in 2018. This refers to a unique topology of network installed in shopping regions to collect data for retail intelligence. With the rise of online retail world-wide the brick & mortar retailers have been hit badly. The basis reason for losing the online vs offline war by later is inability to understand data.

MIN as a practical way to establish a data network that possess capabilities of capturing offline retail data, same is processed & made ready for [Intelligence (AI).] The intelligence from such networks are meant for malls, its allied retailers, brands & 3rd parties for enhancing customer experience. The system can work in clusters or geo fences which are interconnected using [world network]. MIN is scalable to cover global canvas of retail with data privacy as highest priority.

The data captured through sensors, APIs such as weather, traffic, inventory, sales & structured data of profiled customer segments will give a robust insight for retail. MIN has capabilities to scale with time while formulating following parameters were kept in purview which enable the machine learning model to build first of its own kind artificial neural network for retail intelligence.

Big Data

  • Customer Footfall by 3D Camera/Euclid
  • Mac ID of Smart Phone over WiFi
  • Location Timestamp at Each Point
  • Footfall Flow in a Mall w.r.t Layout
  • Dwell Time with Type of Brands
  • Dwell Time with Category of Stores
  • Dwell Time with Type of Malls

Spatio-Temporal Data

  • Geographic Segmentation
  • Traffic Data
  • Weather Data
  • Economic Data

Labelled Data

  • Age Segment
  • Gender Segment
  • Purchase Activity Pattern
  • Reviews & Ratings
  • Cross Shopper Behaviour

The novelty of the network lies in the usage of multimodal data (traffic data, 3D Camera, mac-id, image, temporal, weather & other labelled data) acquired during consumer shopping behaviour measurement using Mall Intelligence Network. This enables machine learning model to build a customised shopping recommendation service. This approach for making recommendations is useful for bringing profits in brick & mortar retail.

A Machine Learning driven intelligent system and method for interpreting consumer behaviour of a user in a community shopping place. The user shopping behaviour data can be captured through a unique identifier as per privacy norms. This is to enhance the shopping experience for customers by sharing highly customised recommendations with business to build engaging experiences with shoppers.

Both Structured data and Unstructured data is used in the Algorithm design. Structured data is the use of consumer spend patterns, shelf time spent, promotional offers consumed and so on. Unstructured data refers to image, video and shopping patterns gathered from consumer movement in inter and/or intra mall locations.

With different size of training datasets the MIN can be optimised every day in the world of retail.

What is claimed using Mall Intelligence Network:

A method for predicting shopper traffic & behaviour at a shopper region useful for developing inter alia a metric for measuring critical path to purchase ensuring shopper privacy, comprising the following steps:

(a) obtaining actual shopper traffic data at a first shopper region at a first retail store, wherein the first shopper region comprises at least a first product category: (b) obtaining actual market data from the first store, wherein the market data comprises category purchase data from the first product category: (c) inputting the shopper traffic data and the market data in an analysis program executable on a computer; (d) training the machine learning program to develop a mathematical model capable of predicting shopper traffic at the first shopper region of a target retail store. (e) executing the analysis program to develop a mathematical model capable of predicting nearest neighbour mapping for k-means to predict shopper traffic at the first shopper region of a target retail store.

The method of claim, wherein actual shopper traffic data at a first shopper region is further obtained at a plurality of retail stores, wherein the first shopper region of the plurality of retail stores comprises the same first product category.

The method of claim wherein said actual shopper traffic data and said actual market data is obtained during the same period of time; and wherein the market data further comprises at least one of the following: Store purchase data, store data, temporal data, demographic data, actual shopper traffic obtained electronically using a fixed sensor or combinations thereof.