ML Contact Time Engine for Consistent Debt Collection Scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing debt collection methods rely heavily on historical data and debtor preferences, which can be subjective and variable, leading to inconsistent outcomes and potential debtor annoyance, making it challenging to determine optimal communication times.
Innovation Solution
A machine learning-based computing system, the contact time recommendation engine, uses inputs from users to extract data, compute contact feature scores, and determine optimal communication times using a gradient descent-based machine learning model, considering factors like incoming call scores, user preferences, and productivity rates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If historical data and debtor preferences are used to determine optimal contact times, then some level of personalization is achieved, but the results become subjective and inconsistent
Solution Approach 1:
The patent replaces manual analysis of historical data and subjective judgment with an automated machine learning system. The ML model objectively processes debtor behavior patterns, call outcomes, and preferences to generate consistent optimal contact time recommendations, eliminating human subjectivity while maintaining personalization.
Solution Approach 2:
The system incorporates feedback loops where call outcomes and debtor responses are continuously fed back into the ML model. This allows the system to learn from past interactions and refine its contact time predictions, improving both consistency and personalization over time through data-driven adaptation.
2Productivity
If frequent communication is used to improve debt collection, then recovery rates may increase, but debtor annoyance and relationship damage increase
Solution Approach 1:
The patent implements dynamic contact scheduling where the ML model adjusts communication frequency and timing based on real-time debtor responses and behavior patterns. The system adapts to each debtor's unique characteristics, increasing contact frequency when it promotes recovery while reducing it when debtor annoyance is detected, balancing productivity with relationship preservation.
3Loss of information
If manual analysis of debtor behavior patterns is performed, then some level of insight is gained, but the process is time-consuming and lacks precision
Solution Approach 1:
The patent replaces manual behavioral analysis with an automated machine learning system that processes large volumes of debtor interaction data rapidly. The ML model identifies subtle behavior patterns and predicts optimal contact times with high precision, delivering comprehensive insights fraction of the time required for manual analysis.
Data Source
AI summary
A machine learning based computing method for computing optimal contact times for contacting first users including debtors, is disclosed. The machine learning based computing method includes: receiving inputs from second users including debt collectors; extracting data associated with the first users and the second users from databases, based on the inputs received from the second users; computing contact feature scores based on the extracted data associated with the first users and the second users, for each specified interval of a contact prediction window; computing first user call scores for each specified interval of the contact prediction window based on the contact feature scores for each specified interval of the contact prediction window, using a machine learning model; and computing the optimal contact times and a prioritized list of the optimal contact times by ranking each specified interval of the contact prediction window associated with the first user call scores.