Earnix Blog > AI

Customer Experience and Machine Learning: Practical Applications

Jonathan Moran

4. January 2018

  • AI
  • Customer Centricity
The notion of using analytics to improve customer experience has changed the landscape and thought process of businesses over the past several years. As machine learning becomes further democratized, or more pervasively available, it is making its way into many enterprise software applications – including the Earnix software suite. Machine learning is impacting everyday analytical activities for our customers (segmentation, modeling, and optimization), and is improving very specific marketing program results. Often the ultimate goal of these marketing programs are to improve the customer experience – which requires a faster, more accurate, and more contextual customer interaction – which is better for both consumer and brand. I’ll give a few examples of how machine learning is improving the customer experience through next best offer personalization, customer behavior analytics with new data sources, and analytical optimization. Results include improved business metrics and KPIs, better sales revenues, and overall happier customers. My examples are specific to Earnix clients – financial services organizations (banks and insurers) around the world.

Next Best Offer Personalization

Using Machine learning with predictive models helps banking personalization with an extreme amount of certainty. It improves the predictive modeling of today by allowing improved analysis against larger customer data volumes. The result:
  • Certain segments of banking customers are receiving tailored offers initially instead of irrelevant non-contextual offers that have a low probability for conversion. Because large volumes of customer data can be used as analytical model inputs, probabilities and propensities are calculated more quickly upon offer creation rather than further down the journey. More data in this instance combined with better algorithms produces a superior result.
  • Data and analytics has allowed a regional banking customer of Earnix to better understand customer preferences – including preferred rates and terms – making the entire process more efficient for both bank and customer. If a bank knows what a customer’s preferred origination rates and terms are, they can get to the close faster, which improves customer satisfaction, and save the bank valuable time.

Customer Behavior Analytics with New Data Sources

Using machine learning in combination with new data sources, whether it is internet of things (IOT), telematics, geographic, or social data is leading to an augmentation of the customer profile and an increased understanding of how and why an insurance customer behaves in the manner that they do. Knowing customer needs and preferences at a deeper level results in:
  • Property and casualty Insurers can use vehicle data to better understand the best policies to offer drivers. No longer does the sixteen to twenty five year old male automatically get the highest premium. Telematics data provides large data volumes that can be classified and applied as inputs to regression models to understand acceptance propensity for certain policy terms. Gems from these large data volumes can more easily be mined and leveraged in marketing campaigns and service interactions to increase customer success metrics such as retention and loyalty.
  • Health and Life insurers are collecting device data from fitness devices (pending opt in) and combining it with random forest and gradient boosted machine learning models to better segment and classify customers for certain fitness or wellness programs. Being able to use device data to monitor health and better classify patients for certain wellness programs or policy discounts creates a customer and brand partnership to better manage health and wellness outcomes.

Analytical Optimization

Optimization based on analytic algorithms is not priority or business rule based, but is instead rooted in operations research and analytical algorithms, helping financial services companies we work with not only understand how a customer may behave or act, but also how they as a brand may need to move relative to the market or industry in the future. The result:
  • Financial services companies are using machine learning algorithms (random forest and gradient boosted models) to predict the probability to be ranked in a certain place (i.e. top 3) in an aggregator portal for financial services products (policies, bank cards, loan rates, etc.). Being able to reverse engineer placement on an aggregator portal makes translates directly to better offer conversion rates.
  • Insurance companies are using machine learning models to predict mid-term cancellation rates on policies. Knowing what percentage of the customer population will attrite or cancel impacts not only how they are interacted with in the present, but also helps companies understand what needed new sales volumes are required in coming months. If you can understand a customer’s behaviors now, you can prescribe a plan to increase their loyalty for the future.
These are the practical applications we are seeing today, mainly where machine learning operates behind the scenes – as an accuracy, speed, and efficiency enabler. It improves on existing methods – because it can increase confidence in analytical output – by using an increasing amount of data and a better, more detailed analytical algorithm to get to the end result. But what may happen in both the near and long term with regard to the intersection of machine learning and customer experience? I will tackle this question in my next blog on the topic – Customer Experience and Machine Learning: Future Roadmaps

The Evolution Revolution

The digital consumer of today expects personalized, transparent, consumer-friendly interactions with brands. Brands are dealing with unparalleled new data sources and volumes, increasing regulations, and new entrants with unique business models disrupting their industries. As the market changes rapidly for banks and insurance companies, they must use analytically-based decision making processes to evolve. Earnix is helping organizations evolve to meet the market revolution of today. Combining traditional analytics with new advanced analytics methods, machine learning, and new data sources and technologies – Earnix is ready to provide the next generation of analytical pricing and product solutions designed for the financial services industry. Using Earnix's customer behavior analytics, brands can deliver significant results by integrating data-driven decision-making into the business process – and win the evolution revolution.

Teilen article:

Jonathan Moran