Automating the manual extraction of financial data from statements using AI; resulting in streamlined workflows, minimized human error, and enhanced productivity for spreading processors.
This page provides a high-level overview of my role and the outcomes delivered; detailed problem framing, process, and design decisions rationale are intentionally reserved for in-depth discussion.
About the Project
Hundreds of attributes need to be fetched manually from financial statements which is time consuming and prone to human error.
​
High Annual volumes of ~60,000 Private Spreads | ~50 FTE supporting CB, CIB | ~200+ attributes & ration need to be manually fetched & calculated from consolidated financial statements | Growing Number of customers | Heavily manual efforts | Error prone and Time consuming
The Challenge
Spreading Processors need a quick and efficient way to extract data from financial statements preferably an automated solution because manually extracting data from multiple statements is a tedious, manual and takes too much time from more important work.
My Role
-
Plan and conduct user research, benchmarking existing solutions and processes
-
Create personas, map end-to-end task flow
-
Determine improvement areas and opportunity to leverage LLM/AI
-
Translate concepts into user flows, wireframes, mockups and prototypes
-
Conduct usability testing, and push adoption by monitoring user feedback
-
Helped in data labeling exercise to determine effectiveness of AI
My Approach
-
Structured the project around the core phases: Discovery, Ideation, Design, Feedback, and Implementation to ensure a user - centered and iterative process.
-
Developed a research plan customized to the unique requirements of the Spreading CoE, beginning with a clear and actionable problem statement.
-
Conducted secondary research by analyzing intranet resources and existing documentation.
-
Employed guerilla research techniques for rapid, informal insights to supplement formal findings.
-
Engaged users through interviews and seat rider sessions to capture authentic needs, behaviors, and pain points.
-
Recorded and analyzed user interviews to validate the current spreading process and uncover real challenges.
-
Aggregated all available data and insights related to the problem, ensuring a 360-degree view of the user experience and operational context.
-
Mapped the existing workflow, systematically documenting pain points and identifying areas for improvement and innovation.
-
Created prototypes and mockups informed by user interview findings, enabling quick validation and iteration. Mockup Link
-
Designed high-fidelity mockups to illustrate the envisioned future state, aligning with user needs and business objectives.
-
Developed a detailed Banker Persona to understand the end-user’s decision-making process and information requirements.
-
Ideated a pre-spreading financial overview feature, empowering bankers with instant access to key ratios and metrics for faster, more informed credit decisions. Banker Persona Concept
-
Proposed a solution that streamlines the spreading process, reduces SLA turnaround time, and alleviates backlog, delivering measurable value to both bankers and the spreading team.
The Result
-
Reduced turnaround time by 60%
-
Efficient risk assessment and improved client experience