In what ways can Socure refine its Sigma Identity Fraud solution to better detect synthetic identities?

Introduction

To refine Socure's Sigma Identity Fraud solution for better synthetic identity detection, we need to analyze the current product, understand user needs, and develop innovative solutions. I'll explore key stakeholders, pain points, potential improvements, and metrics for success. Let's dive in.

Step 1

Clarifying Questions (5 mins)

• Looking at Socure's position in the market, I'm thinking they might be facing increased competition. Could you share insights on how Socure's Sigma Identity Fraud solution currently compares to competitors in synthetic identity detection?

Why it matters: Determines if we need to focus on catching up or maintaining a lead Expected answer: Socure is a leader but facing pressure from new entrants Impact on approach: Would prioritize innovative features to maintain market leadership

• Considering the evolving nature of synthetic identity fraud, I'm curious about the current detection accuracy. What are the false positive and false negative rates for synthetic identity detection in the Sigma solution?

Why it matters: Helps identify whether to focus on improving precision or recall Expected answer: False positive rate around 2-3%, false negative rate unknown Impact on approach: Would prioritize reducing false negatives if they're high

• Given the complexity of synthetic identity detection, I'm wondering about the data sources. Can you provide an overview of the types of data Socure currently uses in its Sigma Identity Fraud solution?

Why it matters: Identifies potential gaps in data sources that could improve detection Expected answer: Uses credit bureau data, public records, and digital footprints Impact on approach: Would explore incorporating new data sources if gaps exist

• Thinking about the product lifecycle, I'm curious about recent feature additions. What major updates or new capabilities has Socure added to Sigma Identity Fraud in the past year?

Why it matters: Helps understand the current product trajectory and identify areas for improvement Expected answer: Added machine learning models for behavior analysis Impact on approach: Would focus on enhancing and optimizing existing features rather than adding entirely new ones