Analytics & Insights, Augmented Analytics, Business Intelligence, Customer Success, Machine Learning

Top 10 Financial Services Firm Accelerates Credit Risk Analysis with Augmented Data Insights

The Opportunity: Evaluate Consumer Risk Using Expansive Data Beyond Credit Scores

The data analytics team in the credit risk department at this Top 10 financial services firm is responsible for the analytical capabilities related to credit risk strategy. The team serves multiple products, including mortgages, consumer credit cards, and small business loans. They were looking for faster and easier ways to evaluate credit risk by using more customer data available to them beyond just credit scores, so the firm can expand credit to more customers and reduce credit losses by identifying behaviors consistent with higher risk.

Challenges: Complex Data, Manual Analysis, Complicated Workflow with Disparate Tools

The challenges presented by the data analytics environment were extensive. Performing an analysis of customer behavior often required examining as many as 300 variables. Because this analysis was conducted manually, identifying the variables which were most important often focused on a subset of the data instead of analyzing all the data, or ended up taking days to complete.

While the data analytics team has a variety of tools to help them with different tasks – including data preparation, machine learning, Python code, and visualization – utilizing multiple discrete tools created friction in the overall analytical process, as data needed to be moved back and forth between applications, which made iterative worfklows difficult to work with. In addition, there is typically just one specialist for each tool, so internal resources were a bottleneck for analytics requests. Some analyses took as many as 5 days to complete.

 

“Tellius has helped us save $700k per month in mitigated losses in one credit product – and we serve many products. The team has reduced the time it takes to identify the most significant credit risk factors amongst hundreds of variables from days to minutes.”

– Director of Analytics, Credit Risk, Top 10 Financial Services Firm

 

Why Tellius

The data analytics team at the firm loves using Tellius for the following reasons:

  • Guided Data Insights. Automated data analysis enables the team to easily examine every data point to discover important patterns, identify variables of statistical significance, and uncover the reasons why performance metrics change. The system utilizes machine learning algorithms to analyze even the largest of data sets efficiently without the need to write code. Users can quickly shape and re-run analysis by selecting variables to be specifically included or excluded from the analysis. Instead of spending days performing data analysis across multiple tools, or drawing conclusions from incomplete data, risk factors can quickly be identified across all the data in a unbiased, transparent way.
  • Unified Analytics Workflow. Tellius gives the data analytics team complete end-to-end capabilities from bringing in data from multiple sources, preparing data, analyzing data with machine learning, and sharing content with business teams. With all this critical functionality in a single product, Tellius eliminates the friction that exists when using multiple tools, data is available to all users and every analysis after being prepared one time, and the workflow is more efficient, especially when going back and forth between steps.
  • Data Performance at Scale. Tellius easily handles data sets that are both large (billions of rows) and wide (hundreds of variables). Analysts cleanse, prepare, and join data sets with point-and-click ease and flexibility of SQL and Python code. The analytical engines in Tellius are optimized for both machine learning analysis and interactive exploration at scale, allowing the firm to overcome the data limitations of legacy statistical applications and visualization tools.
  • Ease of Use for All Roles. Tellius provides powerful capabilities in a user experience that is accessible to every user across the organization. Every data analyst can benefit from the end-to-end analytical functionality without having to become a specialist for a point application. Business users can utilize advanced analytical capabilties by asking questions in a search interface and perform their own ‘why’ type of analysis and customer segmentation, in addition to consuming visual outputs created for them.
  •  

    “Tellius is a complete end-to-end analytics product that combines five existing tools into one. We have gained 1000s of hours in productivity due to the streamlined workflow, automated data analysis, and ease of use.”

     

    Implementation Highlights

    • 50+ Users: Credit risk data analytics team, Business users in each credit product area
    • 300+ Variables: Customer credit risk is analyzed in data sets with billions of rows of data and hundreds of variables
    • Days to Seconds: Complex analysis across 300+ variables is completed in minutes with a streamlined workflow
    • Breakthrough ROI: The firm has gained 1000s of hours in analytics productivity and more than $700k per month in mitigated credit losses

    Tellius has enabled the data analytics team to get 10x faster insights, reducing data analysis from days to hours, whereby gaining 1000s of hours in productivity. Through improved credit risk insights, one of the many departments that use Tellius has saved $700k per month in mitigated credit losses.

     

    Download Top 10 Financial Services Credit Risk Analysis Customer Success Story in PDF.

share

Leave reply

Read Similar Posts

  • Customer Success

    iPhone of Analytics

    If you were even remotely aware of your surroundings in 2007, you almost certainly remember

  • Customer Success

    Decision Intelligence vs Business Intelligence: How I Learned to Stop Digging Through Dashboards and Love Insights

    Me after looking at looking at my 50th revenue chart of the day Data has been

  • Customer Success

    Finding the NBA's most undervalued players

    In 2003 Michael Lewis came out with a book called Moneyball: The Art of Winning