Sales Prediction System Using Visitor Event Segmentation
Solution Overview
Problem
Current analytic systems and lead scoring methods fail to predict sales and company engagement levels, relying solely on past purchase history of known contacts and limited data sources, without forecasting product or service purchases.
Innovation Solution
A computer-implemented sales prediction system that collects and analyzes data from multiple channels to calculate sales prediction scores for both known and unknown visitors, using weighting models based on past purchase behavior to predict future sales and opportunities, identifying spikes in scores for marketing purposes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional lead scoring methods are used, then known contacts can be scored based on past purchase history, but sales prediction accuracy deteriorates because the system cannot predict future sales or score companies
Solution Approach 1:
The system segments visitors into known contacts and unknown visitors, applying different scoring approaches to each group. Known contacts are scored based on their purchase history, while unknown visitors are scored based on their engagement patterns and behavior indicators. This segmentation enables the system to handle diverse data types and predict sales for both groups effectively.
Solution Approach 2:
The system transitions from traditional one-dimensional lead scoring (based solely on past purchases) to a multi-dimensional approach that incorporates various engagement indicators such as website visits, content downloads, email openings, and social media interactions. This dimensional expansion allows the system to predict future sales by analyzing patterns across multiple data dimensions.
2Ease of manufacture
If only past purchase history of known contacts is used, then the system is simple to implement, but it fails to predict future sales and cannot score companies
Solution Approach 1:
The system performs preliminary actions by continuously collecting and analyzing engagement data from multiple sources before sales occur. It establishes baseline scoring models using historical data and then applies these models to predict future sales. This preliminary preparation enables reliable predictions without requiring complex real-time analysis during the sales process.
Solution Approach 2:
The system incorporates feedback loops where actual sales data is fed back into the scoring model to continuously refine and improve prediction accuracy. This feedback mechanism allows the system to learn from past sales outcomes and adjust its scoring algorithms, thereby improving reliability while maintaining operational simplicity.
3Productivity
If limited data sources are used, then data collection is simple, but the system cannot provide comprehensive sales predictions or identify company-level opportunities
Solution Approach 1:
The system merges data from multiple diverse sources including website analytics, email marketing platforms, social media data, CRM systems, and third-party data providers into a unified scoring model. By combining these data streams, the system achieves comprehensive sales predictions and company-level insights that cannot be obtained from any single data source alone.
Solution Approach 2:
The system creates a universal scoring framework that can process and analyze various types of data from different sources using a common methodology. This multi-functional approach allows the same scoring engine to handle diverse data types (web behavior, email engagement, social media activity) and produce consistent sales predictions across different customer segments and industries.
Data Source
AI summary
Computer implemented sales prediction system collects data relating to events of visitors showing an interest in a client company from plural data sources, an organization module which organizes collected data into different event types and separates collected event counts in each event type between non-recent and recent events occurring within a predetermined time period, a first processing module which periodically calculates weighting for each event type based on recent and non-recent events for the event type compared to totals for other selected event types, a second processing module which periodically calculates sales prediction scores for each visitor and companies with which visitors are associated based on accumulated event data and weighting, and a reporting and data extract module which is configured to detect variation in sales prediction scores over time to identify spikes which can predict upcoming sales and to provide predicted sales information and leads to the client company.



