Asset Publisher

Liferay DXP

Dunn Solutions is a Gold Liferay Services Partner and our portal developers and theme designers help companies achieve rapid business value from Liferay's all-in-one package of built in-features including: content publishing; document management; enterprise collaboration; and social networking capabilities - all in a user-friendly portal environment.

  • Enterprise Java Development
  • Custom API Integration & Development
  • Specialization in Enterprise Portal Development
  • Security: HIPAA & PHI Certified
  • Liferay Enterprise and Community Experience
  • Performance Monitoring: Metrics & Insights
  • Award-winning UX Design
  • Enterprise Portal Development

Form

Liferay Consulting Services Landing Page Form

Minneapolis, MN



8009 34th Avenue South
Suite 1255
Bloomington, MN

Tel: 763-923-2300
Fax: 952-406-8807

Directions
Click here for directions.

Using Machine Learning For Pricing Optimization in a B2B Setting

B2B sellers can charge their customers different prices for the same products, and often can even change the price from one purchase to another with little notice. Obviously, this kind of "price discrimination" creates plenty of opportunities to increase short-term profit. However, it can negatively impact the development of trust needed to establish a long-term relationship with buyers. For this reason, a good statistical methodology should be able to predict the short-term impact of pricing as well as the long term effects of pricing decisions.

B2B pricing decisions differ substantially from those within the business-to-consumer (B2C) market because of the high complexity of the business transactions, where the customer needs to make several-interrelated decisions, and the salesperson needs to be able to "read" the customer mindset before generating a quote.

At Dunn Solutions, we realized that it is this complexity that creates tremendous potential for increasing profits by leveraging machine learning.

This video shows how machine learning can be leveraged to accurately model all these interdependent decisions and maximize profit in B2B!

Add True Content Management to BigCommerce

BigCommerce is the market leading B2B and B2C commerce platform available today – but the complete solution is a combination of both content and commerce! Typically, BigCommerce customers need to edit content quickly and easily, manage workflows and permissions, support multi-language translations and personalize content to different audiences.

Dunn Solutions and e-Spirit deliver an integrated Digital Experience Platform (DXP) which creates a powerful and seamless journey from content to commerce for your customers. In our webinar, we will demonstrate how the FirstSpirit DXP platform offers you intuitive, easy to use editing tools for all desired touchpoints and enterprise CMS capabilities that include:

• Workflow, rights and roles management

• Multi-site and multi-language translations

• Content Localization and personalization

• Publication into multiple target systems

Bill Dunn, President of Dunn Solutions and Michael Gerard, CMO of e-Spirit will discuss the content management features and benefits that the FirstSpirit DXP platform can bring to BigCommerce customers.

Cellular Provider Replaces Manual Processes With Advanced BI Solution

Enterprise Wide Business Analytics Solution Developed

Project: Enterprise Wide Business Analytics Solution Developed
Client: C Spire Wireless

C Spire Wireless, one of the largest privately held wireless communications providers in the United States, serves a large area of the Southeast, and has seen steady year-over-year growth since its founding in 1988. To make the move to the next provider tier, however, the aggressively expanding company needed a competitive edge – better and timelier operational data.

Challenge: Manual Reporting Processes

C Spire Wireless tracked a number of key performance indicators, but the data was manually compiled from a variety of sources. This manual process made it difficult to look at the data historically and see trends. What's more, the data took several days to compile at the end of the month.

The complicated compiling process required a large number of e-mails between department heads, all of whom did research within their transactional systems to provide the needed KPIs. Those KPIs then were inserted into several spreadsheets, and aggregated into a final "Operational Metrics" report for key marketing finance and technical executives. This tedious and error-prone process needed to be revamped to enable a faster, more useful view of monthly performance.

Solution: Implement an Enterprise Data Warehouse

Dunn Solutions Group was selected to build a new enterprise data warehouse to compile the necessary data, and build/deliver the Operational Metrics report. The project team began by building a sophisticated data mart on C Spire Wireless's point-of-sale (POS) data.

This source alone provided extremely valuable insight to customer purchase history, which could be mined for KPIs. Another data mart was built to house data from their inventory and purchasing system (IPS), and conformed to the dimensions of the POS data mart to provide compound sales and inventory metrics. Finally, an existing customer billing data mart was upgraded and conformed so that customer service plans could be easily analyzed alongside the other sources.

Result: Timely and Relevant Data and Insights

Together, these sources – POS, inventory and billing – provide C Spire Wireless with the ability to gauge the effectiveness of their various sales channels (telesales, kiosks, web, physical stores, etc.), as well as the popularity of various plans and devices.

Example metrics from these sources include...

  • Quantity, revenue and cost of goods sold (COGS) for phone sales, accessory sales, trade-in credits, coupon redemptions, repair center adjustments, activation fees and rebates
  • Customer wait time
  • Customer abandons
  • New customers
  • CSR efficiency (telesales and physical stores)
  • Inventory on-hand and on-order, and re-order points
  • Invoicing and purchase orders

Dunn Solutions Group's work at C Spire Wireless continues with new data marts to include metrics on roaming, kiosk payments, equipment insurance, number portability, promotions, customer portal activity, extranet (WebTrends) statistics, third-party equipment-provider fulfillment and customer feedback.

Being in IT for the past 28 years I have seen software and hardware evolve from highly specialized technical tools to everyday common tools used by the masses.  These highly technical tools may be common place, but the advancements we see today are no less amazing.  I love technology, I love cool toys, I love living in the time that I live. 

I also love doing what I do.  My name is Jose Hernandez and I am the Director of Business Intelligence at Dunn Solutions Group.  I have been “playing with” computers since the mid 1980’s and have been with Dunn Solutions Group (then Dunn Systems, Inc.) since 1991.  I have decided to start writing about technology as it pertains to business intelligence and data warehousing.  That said, I will probably dabble in a few other tangential topics.

I was first introduced to computer programming in 1983 when I took my first Fortran class.  Honestly, until then my love of technology centered on home and car stereos.  I was one of those early adopters of killer car audio installations.  We didn’t have BestBuy to get it done back then, we did it ourselves.  This also describes the PC world back then.  It was the Wild West and we developed everything ourselves (because we wanted too)!  Back then you controlled the entire hardware stack and you could make it do as much as your coding skills and imagination allowed you to do.  Equipped with a assembly language or some 3rd generation language, some documentation (on paper), and a cool idea, you were off and running.  I devoted many all-nighters working on “my” cool ideas or typing in code from the back of computer rags, and I loved it.  Getting code to work was my drug of choice.  The thrill of watching a program come to life was all I needed to keep at it for just a few more hours.

Much of the thrill is still the same for me.  I still like playing with technical toys and solving problems with technology.  The big difference is the tools got smaller, faster and cooler.  Today, hardware is amazing and the software we use on that hardware is just as amazing.  This will be the underlying focus of my Blog, I will focus on new technologies specifically as they pertain to business intelligence, and on occasion, I may travel down memory lane to provide perspective on my thoughts.

Jose Hernandez

Director of Business Intelligence

Dunn Solutions Group

 

One to One Messaging  

It could be a title of a movie: “Mission Impossible: Getting the right message to the right people at the right time.” Marketers understand the importance of strategic targeted messaging, and while there still are a lot of companies that practice the “one-size-fits-all” approach, others have started to embrace propensity modeling to create better personalization and achieve higher ROI.  

This application of mathematical models to predict whether someone will take a particular action is a powerful way to identify whom among your audience is most likely to engage in  a particular behavior, and under what circumstances. With the aid of propensity modeling, you can focus your resources on the people for whom engagement will generate a meaningful change in behavior, giving them the nudge they need to pull the trigger.   

Can We Do “One to One” Targeting in Debt Collection? 

Given that propensity modelling is used to generate some desired change in behavior, why should we restrict its application only to marketing activities?  Other industries operating outside of the world of E-Commerce and Retail can benefit greatly from propensity modeling.  The banking industry, for example, can greatly benefit from the implementation of propensity modeling for debt collection efforts – otherwise known as “propensity to pay”.  While banks often have good processes in place for collecting debt, they often lack the insight to decide which processes should be applied to which customers. 

Let’s expand on this concept through the aid of a real case study from one of Dunn Solutions’ financial clients. 

In 2018, a major financial institution in the Midwest commissioned a propensity to pay model to be applied to delinquent accounts (customers who are late in paying their outstanding balance).  They were familiar with the concept of “scoring” customers; however, an earlier attempt at developing an in-house solution had failed to deliver the Expected Return on Investment.   

This came as no surprise.  In fact, most companies are not successful with propensity modelling because they don’t act on their propensity scores in the correct way.  For example, a company might be tempted to target only the delinquent accounts with the highest propensity to pay.  As logical as it may seem, this overlooks  the fact that the majority of delinquent accounts will “self-cure.” This means these accounts might become delinquent simply due to an overlooked due date,  but will immediately course-correct and pay when they realize the error.  These customers might have a high propensity score; however, because they will “self-cure,” companies are wasting money and resources by contacting them. In other words: these customers have a high ability to pay, and will do so without the debt collection efforts of the company.  

This was exactly the scenario in which our client found themselves; they were not finding success with their propensity modeling .  

Dunn Solutions Delivers a Successful Propensity to Pay Model 

Dunn Solutions created an accurate and scalable propensity-to-pay model,  and developed a soup-to-nuts comprehensive strategy for using its outputs.   

To start: Dunn Solutions conducted a full-data-evaluation in order to understand what variables could be used and how the population of interest should be defined.  Based on the outstanding balance of the population of interest, we formulated a “what-if” analysis under different scenarios to understand the possible ROI from the project – for example: if we could increase debt collection by 5%, 10%, or 15%, what would our return on investment be?   

Next, along with the client’s IT team, we designed an efficient data pipeline for regular data ingestion to score delinquent accounts in near real-time, as well as a feedback loop to retrain the model on a regular basis.  Only when these preliminary steps were fully executed, did we move on with the development of the propensity-to-pay model. 

The next step in the process was to develop and test competing models, using an unseen sample of delinquent accounts for validation purposes.  Once the propensity-to-pay model was validated and the accuracy proven, we developed an implementation strategy, and tested it in a controlled experiment.   

We recommended that customers with very high propensity to pay NOT be contacted, as these accounts have the ability to pay and will cure themselves.  Finally, customers with extremely low propensity scores should also be ignored, as they are too far gone for debt collection efforts to be successful. Instead, priority was given to the middle-tier customers, who are really at risk of defaulting permanently, but who could still be persuaded with the right incentive.  

Graph of Customers with Highest Propensity Scores

After a few months of market testing using different incentives, these were the expected annualized results: 

  • 41% improvement in debt collection amounts collected  
  • 49% decrease in outbound phone calls 
  • 18% decrease in accounts sent to external legal debt collection agencies 

The Bottom Line:   While many vendors offer some form of propensity-to-pay modeling solution, the most sophisticated statistical methodology is only as good as its end-to-end solution.  Additionally, if the methodology is not part of a continuous feedback loop that adapts to new situations and learns from new data, your ROI will be low. 

Here at Dunn Solutions we have demonstrated ROI over many different projects by fully partnering with our clients to achieve state-of-the art and customized solutions to meet their unique needs.  Please feel free to contact us with any questions you might have on propensity-to-pay models !