Customer Outcome Prediction via Multi-Channel Interaction Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional contact center prediction systems are inadequate in accurately predicting customer outcomes due to limited data inputs and the heterogeneous nature of interaction data across multiple communication channels, leading to less accurate predictions for customer actions and interactions.
Innovation Solution
A method and system for customer-based outcome prediction that involves receiving and analyzing recordings of past interactions, generating past interaction data, building a predictive model, and applying it to current interactions to predict outcomes, incorporating biographical and behavioral assessment data, including personality type data generated by linguistic-based algorithms, across various communication channels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional prediction systems use limited data inputs from single interaction channels, then system complexity is reduced, but prediction accuracy deteriorates
Solution Approach 1:
The patent combines multiple data sources including interaction recordings, biographical data, purchase history, and behavioral assessments into a unified predictive model. This merging of heterogeneous data from various channels (telephone, email, web, social media) enables more accurate predictions while managing complexity through integrated processing.
Solution Approach 2:
The patent adds temporal dimension by analyzing patterns across multiple past interactions rather than single-point data. It also adds behavioral dimension through linguistic-based algorithms that extract personality traits and behavioral patterns, transforming raw interaction data into multidimensional customer profiles for improved prediction accuracy.
2Reliability
If demographic data from single interactions is used for predictions, then data collection is simplified, but prediction reliability deteriorates
Solution Approach 1:
The system performs preliminary analysis of interaction recordings to generate behavioral assessment data and personality type profiles before making predictions. This preliminary processing transforms raw unstructured data into structured behavioral metrics that can be reliably integrated with demographic and purchase history data.
Solution Approach 2:
The system continuously updates customer profiles by incorporating new interaction data, creating a feedback loop where each interaction refines the predictive model. This iterative process improves reliability by ensuring predictions are based on the most current and comprehensive customer information available.
Data Source
AI summary
A method for customer-based outcome prediction that includes receiving recordings of interactions with customers in a customer group, analyzing the recordings of the interactions to generate interaction data, and building a predictive model using the interaction data, the predictive model identifying a variable relevant to predicting a likelihood of an identified outcome occurring in association with future interactions with customers in the customer group. The method also includes receiving a recording of a current interaction with a first customer, the first customer being in the customer group and analyzing the recording of the current interaction with the first customer to generate current interaction data. Further, the method includes adding the current interaction data to a first customer profile associated with the first customer and applying the predictive model to the first customer profile to predict the likelihood of the identified outcome occurring in association with the current interaction.