Predictive Analytics for In-Flight Deal Pricing Probability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for pricing complex service deals, especially high-valued IT services, are cumbersome and time-consuming due to the complexity of pricing individual services at a granular level, and there is a need for a more efficient approach to assess the probability of winning deals at different price points.
Innovation Solution
A system and method that utilize predictive analytics to assess the probability of winning an in-flight deal by receiving information on price points and metadata, applying a predictive model to estimate the likelihood of winning at each price point, incorporating historical and market data, and using a top-down pricing approach to estimate costs and prices based on peer deals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional bottom-up pricing methods are used for complex service deals, then pricing accuracy at granular level is improved, but the process becomes cumbersome and time-consuming
Solution Approach 1:
The patent inverts the traditional bottom-up pricing approach by implementing a top-down pricing methodology. Instead of aggregating prices from individual service components, the system starts with overall deal-level pricing parameters and decomposes them to service levels, significantly reducing pricing time while maintaining accuracy through predictive analytics models trained on historical deal data
Solution Approach 2:
The patent transforms the pricing process by changing from detailed granular parameter input (bottom-up) to high-level parameter input (top-down). The predictive analytics model uses metadata and historical data to automatically determine appropriate pricing parameters, converting a time-consuming manual process into an efficient automated system that maintains pricing precision
2Manufacturing precision
If detailed granular pricing of individual services is performed, then pricing completeness is improved, but the complexity of the pricing process increases
Solution Approach 1:
The patent segments the pricing process into distinct hierarchical levels: deal level, service level, and service component level. The top-down approach allows pricing to be established at higher levels first, with automatic decomposition to lower levels, reducing overall process complexity while ensuring comprehensive pricing coverage through structured segmentation
Solution Approach 2:
The predictive analytics model serves multiple functions simultaneously: it performs probability of winning assessments, determines optimal price points, validates pricing completeness, and guides the top-down pricing process. This multi-functional approach reduces the need for separate complex processes while maintaining comprehensive pricing coverage
3Measurement precision
If probability assessment for different price points is conducted using traditional methods, then assessment accuracy is improved, but the agility and efficiency of the process deteriorates
Solution Approach 1:
The system performs preliminary actions by pre-training predictive analytics models on extensive historical deal data before actual pricing decisions are needed. This pre-computation of probability relationships enables rapid, accurate probability of winning assessments for multiple price points during the actual pricing process, significantly improving efficiency without sacrificing accuracy
Solution Approach 2:
The patent uses historical deal data as copies of past pricing scenarios to train predictive models. These trained models then serve as virtual replicas of successful pricing patterns, enabling the system to rapidly assess probability for new deals by comparing against learned patterns from historical copies, thereby improving both accuracy and efficiency
Data Source
AI summary
One embodiment provides a method for assessing probability of winning an in-flight deal. The method comprises receiving information for the in-flight deal. The information for the in-flight deal comprises a set of price points for the in-flight deal and metadata relating to the in-flight deal. The method further comprises, for each price point of the set of price points, predicting a probability of winning the in-flight deal at the price point based on a predictive analytics model.