Leveraging AI/ML for Suitability Review of Mutual Fund Applications for a Fortune 500 Financial Services Company

[vc_row type=”image” bg_gradient=”yes” padding_top=”0″ padding_bottom=”0″ el_class=”innerBanner Csbanner” bg_image=”11012″][vc_column][vc_column_text]

[/vc_column_text][/vc_column][/vc_row][vc_row type=”image” bg_repeat=”repeat” bg_cover=”false” el_class=”customer-sec common-sec ds-container common-h2 bChallenges” bg_image=”350″][vc_column][vc_row_inner el_class=”customer-content risk-content”][vc_column_inner][vc_column_text]

Business Objective

[/vc_column_text][vc_column_text]Our client is a US Fortune 500 diversified financial services firm with more than 100 years in business. It offers consulting, investments, insurance, banking, and generous programs and solutions to help individuals make the most of what they have. They oversee $189 billion in assets.

The client used a rule-based decision engine to determine mutual funds application suitability. The client wanted to improve the ‘Mutual Fund Applications Approval’ process. The objectives were:

• Reduce manual efforts
• Minimize incorrect labeling of decline or not in good order (NIGO) applications

[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row type=”image” bg_repeat=”repeat” bg_cover=”false” el_class=”data-approch-sec common-sec common-container common-h2 challengeContent” bg_image=”1909″][vc_column][vc_row_inner el_class=”approach-content”][vc_column_inner][vc_column_text el_class=”busi-balck-content”]

Challenges

• Approval rate by the decision rule engine was lower than expected
• Process involved significant manual intervention
• The rules engine could not manage complex data like free text
• Current rules did not capture complex relationships in data

[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row type=”image” bg_repeat=”repeat” bg_cover=”false” el_class=”data-approch-sec common-sec common-container common-h2 solutionMethodology” bg_image=”350″][vc_column][vc_row_inner el_class=”approach-content”][vc_column_inner][vc_column_text]

Solution Methodology 

Carried out a thorough study of the client’s challenges and existing workflows to design the solution-

• Identified additional data, including attributes on Financial Planners, client demographics, Salesforce documentation, application details, and Asset Transfer Disclosure (ATD)
• Used this data to hypothesize regarding the reasons for follow-ups required on an application, which would eventually require an increase in the manual efforts
• Trained an AI/ML model on this augmented data to identify the additional applications that can be auto-approved without contradicting any existing business rules
• Rebuilt the Decision Engine combining the existing business rules with AI-driven insights to improve the application review process

[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row type=”image” bg_color=”#161717″ bg_repeat=”repeat” el_class=”data-approch-sec common-sec common-container common-h2 bImpact”][vc_column][vc_row_inner el_class=”approach-content”][vc_column_inner][vc_column_text]

Business Impact

• 15% point increase in the number of applications approved automatically
• Reduction in misclassification on the application decline/NIGO reasons
• AI-augmented decision engine with the ability to handle complex data and exploit hidden patterns
• Annual cost savings of $100K
• Manual hours reduced by approx. 29% by improving the auto-approval rate from 43% to 58%

[/vc_column_text][kleo_button title=”Download Case Study” target=”_blank” style=”custom” icon=”0″ el_class=”dcsBtn popmake-11944″][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row]