Interested in bringing more intelligent pricing to your bank?
Here are some of the concepts you should be considering in your banks pricing processes.

Pricing Science icon_Hazard Rates.png
Hazard Rate

Hazard Rates are a cornerstone of modern intelligent price optimization. They reveal what percentage of a population will take up or attrite from an offer at that price point. With the Nomis approach, Hazard Rates are exposed to the pricing end user so there is a clear understanding of how optimal rates are being derived.

Pricing Science icon_Saturation.png

Saturation represents the maximum prediction values in a predictive model. In pricing optimization, a saturation parameter estimates the total market demand for a given pricing cell in a product. For example, the demand for a deposits product from a bank cannot exceed the total demand in the entire market. 

Why is this important?

Saturation parameters are an important feature of pricing models to ensure they realistically predict the outcome of pricing movements by bounding estimates to no more than the total expected demand in a given pricing cell/local market. 

They are an important ‘safety check’ in optimization efforts to ensure models don’t recommend unrealistic scenarios.

Efficient Frontier icon
Efficient Frontier

Similar to the efficient frontier developed in modern portfolio theory, the Efficient Frontier in pricing optimization specifies the best outcome (be it maximizing volume growth, or maximizing net interest margin, or reducing interest expense) that can be achieved given the tradeoff you would be willing to accept (e.g. interest expense, volume, balance run-off, etc.)

Why is this important?

The efficient frontier is our framework to determine whether banks are pricing optimally – in deposits, that is best trading off volume growth for the level of interest expense paid; in lending trading off interest income for volume of assets.

Banks should strive to set prices where outcomes fall onto their efficient frontier.

Pricing Science icon_Price Sensitivity Dispersion.png
Price Sensitivity Dispersion

Price Sensitivity Dispersion measures the variation in price sensitivity across segments.  

Why is this important?

The higher the dispersion, the greater the financial impact that can be achieved by optimizing prices.

Pricing Science icon_Balance Distribution Entropy .png
Balance Distribution Entropy

Entropy basically measures how distributed or concentrated your balances are across your pricing segments. If all balances are concentrated in one pricing cell, “balance entropy” is 0.  If balances are distributed evenly across all your pricing cells, it is 1. The general notion is that the more the “entropy”, the greater the opportunity to optimize.  

Why is this important?

The higher the entropy, the greater the financial impact that can be achieved by optimizing prices. Conversely, a low entropy denotes a concentration of volume in a limited number of segments or pricing cells limiting impact of price optimization efforts.

Adverse Selection.png
Adverse Selection

In the lending world, adverse selection occurs when a bank’s increase in loan rates results in a deterioration of the credit quality of the customers that do accept the loan. This is because the loan offering becomes less attractive to higher quality customers with access to relatively lower cost loan programs.

For instance, an increase of 0.25% in the interest rate of a home equity loan therefore not only decreases the number of customers willing to accept the loan, it also results in the customers likely to accept loans at the higher rate tending to have lower credit quality. 

Why is this important?

Your pricing optimization process needs to be able explicitly measure, manage and limit adverse selection effects in setting prices.

Nomis Score

Nomis Score for Deposits is a proven, customer-level price-sensitive response scoring methodology specifically designed for deposits-related customer decisions. Think of it as a hazard rate for each of your customers. It enables Deposits Product, Pricing & Marketing teams to understand how different customers are likely to respond to key deposits-related events, identify those customers that represent the greatest risk or opportunity and develop personalized treatments that drive the right outcomes for both the bank and the customer.

Contextual versions of the Nomis Score can be applied across a spectrum of deposits problems, including:

  • Run-off / Re-pricing Risk Management: Identify customers who are most likely to churn and move balances elsewhere as interest rates rise
  • New Money Promotional Offers: Identify customers who are most likely to respond favorably to new money promotional offers
  • Post-promotional Retention Management: Identify “hot money” customers who are highly likely to move their money out once the promotional period ends
  • Time Deposit Renewal Management: Identify customers who are more likely to redeem their CDs and take their balances elsewhere

The Nomis Score combines standard CIF attributes along with customer/account-level data on transactional behavior, relationship and engagement markers from your bank with Nomis proprietary 3rd party data on consumer needs, priorities and preferences. The data elements may be adjusted depending on the use case or business challenge the bank is looking to address as well as data availability. Nomis’ Big Data & Analytics Engines then used to calibrate the Nomis Score to ensure strong rank-ordering. Unlike first-generation approaches that fail to find meaningful price sensitivity differences in Deposit portfolios, the Nomis Score approach reveals as much as a 126X difference in price sensitivity between the least and most price sensitivity customers.

Get Started with Nomis Index – Real Insights about your Portfolio Right Now »