S-MALL Future Work

Turning Concrete Malls into Smart Malls (S-MALL):
A web-based analytics application for visualizing and mapping in-mall customer journeys and shopping behaviours

Team S-MALL: Chen Yun-Chen | Chiam Zhan Peng | Zheng Bijun

Overview

Application

Poster

User Guide

APPLICATION

Movement Analysis

Member Analysis

Association Analysis

GUIDE

Part1: Movement Analysis

Screenshot	Guidance
	Plot by and Segment by are for line chart. Choose segment to show cycle plot. View is to show flow between each floor and hexbin map in a particular time.
	Hover on lines to show detail in formation.
	Hover on the graph to show detail in formation. Example: There are 61 customers moving from 3F to 2F and 57 customers moving from 2F to 3F at selected time.
	Click on hexbin and click button Show Detail to show the distribution as following in selected hexbin.
Error creating thumbnail: File with dimensions greater than 12.5 MP	Click on bar to show detail information in table as following.
	Count means the customer stays in selected hexbin for how long (min) in selected time interval.

Part2: Member Analysis

Screenshot	Guidance
	Selection All in Operating Hours: All members Selection Normal in Operating Hours: Members who only appear in operating hours. Selection Outside in Operating Hours: Members who appear out of operating hours. Exclude dwell time less then: This control panel is for Shopper's Journey. User can exclude those records which only stay in a particular floor for a few minutes. Profile Count by: This control panel is for member distribution. Non-Unique Customers: Count by records. Unique Customers: Count by member ID.
	Hover to see the path and relevant statistics. Example: There are 23 of 2.2k journeys which start from FLOOR M and go to FLOOR G then go to FLOOR 2.
	Click on floor level to drill down to store level. Click on any store to show the relevant boxplot for selected floor as following.
	Select records you are interested in to show the relevant distribution(bar chart) as following.
	Get the distribution of records in box selection.

Part3: Association Analysis

Screenshot	Guidance
	Set date range using radio button to see the plot of different months. Set parameters (support/confidence/min items) to generate valid associations rules and render plot forquadrant and network.
	Investigate popular shopping path of members based on floors. Hover over the bar to fade out non-relevant rules in the quadrant as following.
	Visualize the associations among departments. Hover over the network to fade out non-relevant rules in the quadrant as following.
	Analyze the competitive position of different rules based on set parameters.
	Detail information of different rules based on set parameters.

Please be patient.