| "deepVoxel's
prediction models for customer behavior had a stunning degree of accuracy. The success of our customer retention
program was directly due to the diligence and technical capabilities delivered by deepVoxel"
-J.S., Customer Information Manager, B2B |
|
Business Solution Examples
The following case examples illustrate how deepVoxel
Analytics has helped commercial clients leverage the power of event analytics:
- Customer retention
- Behavioural response modeling
- Multi-channel analytics
|
|
 |
|
Customer Retention |
Problem: Find customers 'at-risk' for churn.
A multi-billion dollar wholesaler aims to reduce the number of clients that leave, taking their
business to competitors. They need a system that will detect client defection as early as possible,
enabling them to intervene and recover potentially lost revenue.
Solution
Using advanced data-mining methods, deepVoxel develops a highly accurate system to detect customer churn.
Customers who are at risk for defection are identified for outreach to win back both their loyalty and future revenue.
|
Customer Response Modeling |
Problem: Find the most 'responsive' customers
Profitability increases dramatically when customer responsiveness can be predicted. The ability
to distinguish 'persuadable' from 'dead' customers means that companies can focus their efforts on the
customers that are most likely to respond.
Solution
deepVoxel develops algorithms that mine complex, multi-channel transaction data to estimate customer
responsiveness. The high accuracy of these statistical models enable the client to contact only the most
responsive clients.
|
|
Multi-Channel Analytics |
Problem: Use multi-channel data to it's fullest potential
Customer behavior is recorded in a vast number of ways, ranging from point-of-sale
transaction histories to clickstream activity on the internet. Analysts need
to formulate models that leverage all forms of data to create powerful predictors of
customer behavior.
Solution
deepVoxel develops novel visualization technologies to interactively explore
high-dimensional data. These technologies enable analysts to formulate models that are
robust and explainable.
|
Market Basket Analysis |
Problem: Find Targets for Upselling
Which customers are loyal and which ones are 'cherry-picking' your product lines for the best deals?
Are you getting their full share-of-wallet, or are they going elsewhere for their largest purchases?
Solution
The content of a customer's basket of purchases reveals how they are using you as a supplier.
Statistical analysis of their product basket uncovers opportunites for growing your share of their wallet.
|
|
|