SLIDE 1
New Customer Acquisition at Sage: A More Scientific Approach Dan - - PowerPoint PPT Presentation
New Customer Acquisition at Sage: A More Scientific Approach Dan - - PowerPoint PPT Presentation
New Customer Acquisition at Sage: A More Scientific Approach Dan Taylor, Customer Insights Manager UKI Jen Unwin, Customer Insights Analyst UKI What are we going to cover? About Sage Our Analytics Team Preparing to Model Using Enterprise
SLIDE 2
SLIDE 3
Who is Sage?
SALVIA OFFICINALIS SAGE GATESHEAD
SLIDE 4
SAS Users at Sage UKI
SLIDE 5
Analytics in Sage
Descriptive (1981+) Inferential (2000+) Predictive (2010+) Increasing Complexity
SLIDE 6
Direct Indirect Accountant Partner
Who Should We Target?
‘New’ Sage Customers
Vs
Construction Manufacturing Health and social care £0-£20k £21-£40k £10m+ Unknown employees 0-10 employees 200+ employees
‘Non’ Sage Customers Strengths & Weaknesses Core Enhancements Core Enhancements
SLIDE 7
Non-Matched Sage Customers Matched Sage Customers 200+ variables
UK Universe 380k records
200+ variables URN Contactability Target Variables
93 50 299 SSB/AD/SMB S1 Prospects 380k Blind File
The ‘Blind File’ – Start the clock!
SLIDE 8
Analysing the Blind File
SLIDE 9
Modelling in Enterprise Guide: RPM
Modelling Method: Basic, Intermediate, Advanced? Why?
- Over 100 Variables
- Compare several different modelling techniques
Intermediate
SLIDE 10
‘Miner’ Changes
Other Model Types Sample Size Exports Interactive Binning
SLIDE 11
Translation Back to the Business: Binning Node
Modified Bandings Less than 2 Employees 2 - 4 Employees 5 - 9 Employees 10 - 19 Employees 20 - 49 Employees 50 - 99 Employees 100+ Employees Original Model Variable Division Less than 3.5 Employees 3.5 - 44.5 Employees More than 44.5 Employees
SLIDE 12
Returning to the Blind File: Combining Variables
SLIDE 13
Evaluation of Models
SLIDE 14
Direct sales Indirect sales Accountant Partner Web Store Direct Web Model 𝒛
Highest 50% of P values for each model <50% pass >50% fail
Model 𝒚
Average Unit Price (AUP) P value Model Fit = 𝑸𝒘𝒃𝒎𝒗𝒇 𝒙𝟐 × 𝑵𝒑𝒆𝒇𝒎 𝑮𝒋𝒖 𝒙𝟑 × 𝑩𝑽𝑸 𝒙𝟒
Comparing Multiple Models
Model Development Model Reduction Model Translation Model Allocation 33 Models
SLIDE 15
Modelling Process - Takeaways
Expectations The Input File Data Partnership Results Presentation Use the modelling bi-products Learn from Mistakes Use SAS
SLIDE 16