Blog

Cultivating a long-term customer relationship requires intelligent marketing efforts based on a solid understanding of the types of products a particular customer or group of customers would most likely be interested in based on their past behavior. Aunalytics has nearly a decade’s worth of experience assisting our clients with data analysis projects and now offers the fruits of that experience as the Product Propensity Report Framework for our Daybreak™ Analytic Database subscribers. The Product Propensity Report Framework (PPRF) provides a customized dataset with an individualized analysis of every customer’s propensity for new financial services products by type. Think of it like a PivotTable in Excel with a row for every customer and columns representing each of the products your institution offers with a propensity score showing the likelihood that customer might opt for that product.

The preceding example is purely illustrative since every Product Propensity Report is customized to the types of products and services offered by our clients, but it shows the general structure of how such a report might look like for a client offering five different products. In this example, customers receive a decimal score (0-1) for each product, or an indication that the customer already has that product (NA). In this example, we can see that Jane Smith is predicted to be very likely to open a checking account or possibly a credit card account, whereas John Doe and Jill Ramos will likely open a credit card account, and Jack Jones will most likely be interested in a retirement account.

Aunalytics generates these Product Propensity Reports for clients based on a machine learning algorithm that learns about new accounts opened from your organization’s historical data. This algorithm digs into data about transactions and current product utilization to construct a model that can identify future customers’ propensities based on patterns in this data. The output of this model is tailored uniquely to your organization’s product offerings and trained on your organization’s data in order to provide you with reporting that gives you a deeper glimpse into what your customers are after and how best to tailor your outreach to connect those customers with the products and services they are most interested in.

Daybreak™ Insights provide best-in-industry value for analytics platforms by integrating data visualization to display results of AI and Machine Learning powered analytics assessment of your data. Daybreak exists to enable anyone to get data-driven answers to their questions. With easy-to-use tools like Daybreak Natural Language Answers, users without a background in database technology can generate result sets from their data by simply asking questions about the data. No coding, or technical knowledge of databases, datamarts, SQL queries or how to get your data prepped and ready for analysis is needed. Insights are revealed based upon your data in the form of lists of customer records that match your query and also by visualizations to display those results in various graphical forms like line, donut, or bar charts. This tool provides similar capabilities to dedicated BI tools like Tableau or PowerBI, and is available as part of Daybreak. Daybreak also allows you to export analytic results to your favorite BI visualization tool, where your team may have already built custom views and dashboards.

Insights are a valuable way to share stories about data with other members of your organization. The Daybreak Insights dashboard enables you to build a custom dashboard for saved queries, and then share that dashboard with other Daybreak users on your team. Insights can also be saved as downloadable graphics for inclusion in other documents or slideshows to accelerate and automate data-driven presentations.

Daybreak Insights are easy to create. Simply click the “Insights” tab to add an Insight. Daybreak supports different kinds of charts to display different kinds of data, like timeseries line charts, column or donut charts, or summary metrics to display simple calculations based on fields. Each type of Insight has its own settings that can be configured to control how the charts are drawn. The value of each axis or segment can be simple counts of records, or aggregations based on arithmetical or statistical operations like sums, minimums, maximums, or averages.

Insights are one of the many ways Aunalytics provides data-driven answers to your most important business and IT questions.

Our multi-indicator risk model significantly improves upon the accuracy provided by purely statistically-based risk models such as FICO scores and the actuarial tables used by underwriters to set interest rates. Although these basic statistical models are general guides to default risk, our model calibrates and quantifies how those variables and others impact loan defaults across loans of all types. For example, although low FICO scores are predictive of higher risk, how predictive they are depends on other factors such as the type of loan (mortgages, HELOCs, business loans, etc.), term, payment frequency, and so forth. For example, in one model trained using our proprietary algorithm on loan default data from one of our clients, the model discovered that for small business loans, payment frequency was actually more predictive of loan default than credit score. In other words, even borrowers with high credit scores would default on small business loans with monthly payment terms at a rate that wasn’t that different from borrowers with low scores. When payments were made semi-annually, however, credit scores became a much more predictive factor of loan default risk. 

By digging deep into the complex relationships between different loan risk factors, our algorithm can produce impressive results. Performance tests on datasets have shown this algorithm to be highly precise, with one model trained on one of our client’s data the ability to predict 30% of loan defaults in a benchmark dataset with near perfect accuracy (0.99 precision at 0.30 recall) and could return consistently reliable results at higher levels of recall. The loan default risk models trained with our proprietary algorithm provide extraordinary business value to our clients in the financial services industry by flagging risky loans and providing a deeper understanding of risk factors involved with loan applications beyond basic ratings provided by an applicant’s FICO score. 

Aunalytics is a data platform company delivering answers for your business. Aunalytics provides Insights-as-a-Service to answer enterprise and mid-sized companies’ most important IT and business questions. The Aunalytics® cloud-native data platform is built for universal data access, advanced analytics and AI while unifying disparate data silos into a single golden record of accurate, actionable business information. Its Daybreak^TM industry intelligent data mart combined with the power of the Aunalytics data platform provides industry-specific data models with built-in queries and AI to ensure access to timely, accurate data and answers to critical business and IT questions. Through its side-by-side digital transformation model, Aunalytics provides on-demand scalable access to technology, data science, and AI experts to seamlessly transform customers’ businesses.

Customer churn represents lost opportunities as customers move their business to one of your competitors. At Aunalytics, we have nearly a decade of experience developing such models for clients in various industries, including financial institutions. For client subscribers to our Daybreak™ Analytical Database, the churn propensity report Smart Feature^TM offers a uniquely valuable dataset for understanding the risk factors that could indicate customers are about to take their business elsewhere.

The algorithm behind this Smart Feature was developed by studying historical customer churn data from many different client institutions to discover common patterns in the typical behaviors that precede account churn. One key approach to developing this algorithm was to redefine churn beyond simply customers who closed an account; instead, churn was defined to include customers who suddenly drew down a high-balance account and never returned that account balance to its previous level after a period of months. By looking at the data in this way, our data scientists were able to understand that the behaviors that predict churn often happen many months or years before an account is actually closed—for example, a customer stops using direct deposit or bill pay services, then withdraws most of the balance a few weeks to months later but doesn’t actually close the account for a few years.

Based on this deeper look at the data, Aunalytics has been able to develop an algorithm that looks at numerous factors such as customer transactional data, the age of the account, the presence of ACH deposits prior to churn, number of debit card transactions per month, online banking login frequency, and length of the total customer relationship, among others. Once this algorithm is trained on a client’s data, we can provide that client with propensity to churn scores expressed both as a standard percentile (e.g. absolute probability in the range of 0-100%) and a decile score (e.g. a score from 1-10 where 1 is the group composed of the 10% of customers least likely to churn and 10 is the 10% most likely to churn). Using these Smart Features, our clients in financial services can understand immediately what the likelihood is that a customer will churn, or build datasets to target customers at risk of churn with offers and incentives that might keep them actively using those financial products.

Crypto investors tend to be younger adults. They decide to put money into a crypto currency investment with the idea that the currency will gain value over time. When compared to current low and no interest checking and savings accounts rates, where money will not grow in a conventional banking account, crypto provides the promise of potential growth.

People use cryptocurrency for quick payments, to avoid transaction fees that regular banks charge, or because it offers some anonymity. It is typically exchanged person to person online (such as over a phone or computer) without an intermediary like a bank. This means that there is often no one to turn to if there is a problem with the exchange.

While some crypto investment opportunities may be speculative long term plays, unfortunately unscrupulous scammers have been attracted to the emerging industry. Investors may find their investment to be worth nothing and the value stolen by a scammer. New crypto currency brands emerge often and many consumers do not know which are legitimate. Because crypto currency is stored in a digital wallet, it is at risk from hackers stealing it. Because there is no banking intermediary, there is no one to turn to if there is fraud.

Crypto currencies are not backed by the government. So, if you store your crypto with a third party company that disappears or is hacked and your money is stolen, there is little to no recourse and the government has no obligation to help you get your money back.

Unlike with credit card purchases, returns and refunds are often not possible for purchases made with crypto because the unregulated industry does not offer these protections as standard.

Crypto currency values change rapidly and constantly. Value is based upon supply and demand. Unlike many investments that may fall in value but typically regain value over time, crypto is less stable. A purchase of $1000 could fall to a value of $100 in minutes. Conversely, it could rise to a value of $10,000 in minutes. But then it could change again – even while you are trying to cash out on your gain while up, it could result in a loss due to the value changing again before the transaction is complete.

Daybreak^TM for Financial Institutions was built specifically for mid-market banks and credit unions to get business outcomes using analytics. Daybreak can mine your transactional data to determine which of your customers has money leaving or entering your bank from a crypto currency company. This will give you an actionable list of customers for outreach and education on risks. If enriched with a listing of crypto companies known to be fraudulent, targeted outreach may be done by you to save your customers from fraud. Further, after explaining the risks of crypto and educating your customers, you may be able to offer an alternative investment opportunity to keep your customers safe and their dollars in your bank.