Vous êtes sur la page 1sur 36

Network Analysis

For Customer Community Detection


Difficulty: Intermediate

Matt Dancho & David Curry


Business Science Learning Lab
Learning Lab
Structure

● Presentation
(20 min)

● Demo’s
(30 min)

● Pro-Tips
(15 mins)
“I’ve been [messing] around with Python for 4 months.
Success Story I learned more in the 2 days I did Jumpstart with R.”

Josh Nelson

- Friday - Began Jumpstart


- Sunday - Began 101
- Monday - Analyzing
Google Analytics API &
Plotting

#Business
Science
Success
Agenda
● Business Case Study ● 30-Min Demo
○ Customer History ○ Bank Customers
○ Account History
○ EDA
○ Network Analysis
● Network Analysis ○ Machine Learning
○ 2 Types
○ Key Concepts

● Pro-Tips:
○ Tactics to Explain
● R Packages Why Customers
○ tidygraph belong to
○ ggraph Communities
Learning Labs Lab 18
Time Series Anomaly Detection
PRO with anomalize [HOT - 300+ Data
Scientists Attended Live!] Continuous Learning
Jet Fuel for your Brain
Every 2-Weeks Lab 17
Anomaly Detection with H2O
1-Hour Course Machine Learning

Recordings + Code + Slack Lab 16


R’s Optimization Toolchain, Part 2
$19/month - Nonlinear Programming

Lab 15
R’s Optimization Toolchain, Part 1
university.business-science.io - Linear Programming

Lab 14
Customer Churn Survival Analysis
Customer Communities
Business Case
Customers Naturally Form
Communities

Can Be Profitable to
Detect Communities
Customer Communities are Natural
Phenomenon

Detection is really important:

1. Avoid Trap of Focusing on


EVERYONE
2. Customize Products & Services for
Key Groups
Customer History
Descriptive Features
Customers
Network Analysis Basics
80/20 Concepts
Types of Network Analysis

1 2
Undirected Directed

Strength of Relationship Hierarchical Structure

Clustering Composition of
Groups
Types of Network Analysis

1 2
Undirected Directed

Strength of Relationship Hierarchical Structure

Clustering Composition of
Groups
Core Concepts
80/20
Adjacency Matrix

Key Concept
N x N matrix of Relationship
Strength (Measure)
Nodes & Edges

Nodes

● Customers

Edges

● Relationship Strength

Clusters (Groups)

● Densely Connected Web

Key Concept

Groups (Clusters) have


more edges connecting
more nodes at a given
relationship threshold.
Pruning & Threshold

Threshold = 0.9999 Threshold = 0.99


Pruning Too High Too Low
● Filtering to reduce to the
most “influential” nodes

● We use a threshold to
find an optimal
visualization that explains
the groups
Threshold = 0.996
Just Right!

Key Concept

Data mining is subjective.


Where do we cut off?
Network Analysis
Software
tidygraph

Tidy Network Data

● Combines Node and Edge Data inside


1 tidygraph object

● Makes it super easy to work with


network data

● Can activate() inner node and edge tbls


to manipulate them

● Can apply special network analysis


functions like group_components() &
centrality_degree()

https://github.com/thomasp85/tidygraph
ggraph

Visualization Package for


tidygraph data

https://ggraph.data-imaginist.com/
Customer Segmentation Workflow
Step-By-Step

Start Finish
1 2 3

Data Clean & Adjacency Matrix, H2O & LIME


Transform tidygraph, & ggraph Predict & Explain

Exploratory Data Analysis Visualizations Customer Segments

Develop Segments
30-Min Demo
Analyze Customer Networks
Secret Tactics for

Network Analysis
Use these tips to
increase your customer segmentation explainability
Pro Tip
Use H2O & LIME to EXPLAIN WHY
Data Science Transformation
Skills that are needed to do what we just did
Customer Segmentation Workflow
Step-By-Step

Start Finish
1 2 3

Data Clean & Adjacency Matrix, H2O & LIME


Transform tidygraph, & ggraph Predict & Explain

Exploratory Data Analysis Visualizations Customer Segments

Develop Segments
101 & 201 Lab 19
Data Cleaning
201
dplyr, ggplot2

101 & 201


Adjacency Matrix, tidygraph, & ggraph

Lab 19
ggplot2 & purrr

201
Business Science University
Our program that will TRANSFORM YOU in weeks, not years.
The program that will deliver YOUR Transformation
-TRACK 3-Course R-Track System
Business Analysis with R Data Science For Business with R R Shiny Web Apps For Business
(DS4B 101-R) (DS4B 201-R) (DS4B 102-R)

Project-Based Courses with Business Application


Data Science Foundations Machine Learning & Business Consulting Web Application Development
7 Weeks 10 Weeks 4 Weeks

Business Web Apps


Reporting Advanced
Data Advanced
Functional Science Functional
Programming & Programming &
Modeling Modeling

Visualization Advanced
Data Cleaning & Advanced
Visualization Data Wrangling
Manipulation

Business Science University


R-Track
Key Benefits
Business Analysis with R
- Fundamentals - Weeks 1-5 (25 hours
of Video Lessons) (DS4B 101-R)
- Data Manipulation (dplyr)
- Time series (lubridate) Data Science Foundations
- Text (stringr) 7 Weeks
- Categorical (forcats)
- Visualization (ggplot2)
- Programming & Iteration (purrr)
- 3 Challenges

- Machine Learning - Week 6


(8 hours of Video Lessons)
- Clustering (3 hours)
- Regression (5 hours)
- 2 Challenges
Business Reporting

- Learn Business Reporting - Week 7


- RMarkdown & plotly Functional
Programming &
- 2 Project Reports: Modeling
1. Product Pricing Algo
2. Customer Segmentation

Visualization
Data Cleaning &
Manipulation
Key Benefits
End-to-End Churn Project Data Science For Business
Understanding the Problem & (DS4B 201-R)
Preparing Data - Weeks 1-4
Machine Learning & Business Consulting
- Project Setup & Framework
- Business Understanding / Sizing
10 Weeks
Problem
- Tidy Evaluation - rlang
- EDA - Exploring Data -GGally, skimr
- Data Preparation - recipes
- Correlation Analysis
- 3 Challenges

Machine Learning - Weeks 5, 6, 7


- H2O AutoML - Modeling Churn
- ML Performance
- LIME Feature Explanation Advanced Data
Science
Advanced Functional
Programming &

Return-On-Investment - Weeks 7, 8, 9 Modeling

- Expected Value Framework


- Threshold Optimization
- Sensitivity Analysis
- Recommendation Algorithm Advanced
Advanced Data
Visualization
Wrangling
Key Benefits
Shiny Apps for Business
Learn Shiny & Flexdashboard
(DS4B 102-R)
- Build Applications Web Application Development
- Learn Reactive Programming
- Integrate Machine Learning
4 Weeks

App #1: Predictive Pricing App


- Model Product Portfolio
- XGBoost Pricing Prediction
- Generate new products instantly

App #2: Sales Dashboard with


Demand Forecasting
- Model Demand History
- Segment Forecasts by Product &
Web Apps
Customer
- XGBoost Time Series Forecast
- Generate new forecasts instantly Machine
Learning
“This course showed me how to place data
analytics in real business settings.”
Success Story
Masatake Hirono

- Took DS4B 201-R


#Business
- Completed the 10-Week Science
Course Success
- Landed a Job at one of the
most Prestigious
Management Consulting
Firms
15% OFF PROMO Code: learninglabs

-TRACK BUNDLE
Begin Learning Today
university.business-science.io

Vous aimerez peut-être aussi