Strategic-Tactical Segmentation Planner for Stable Supply Chain Policies
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing dynamic segmentation systems face inefficiencies due to frequent, insignificant changes in data, leading to longer lead times, confusion in segmentation results, and unnecessary change management protocols, resulting in sub-optimal supply chain inventory allocation and service levels.
Innovation Solution
A strategic and tactical segmentation system that utilizes a segmentation planner to manage input data comprehensively or with a representative sample, autonomously generating and updating segments while maintaining segmentation boundaries, using machine learning models to predict segment intersections and adapt to significant data changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If dynamic segmentation is used to speed up segmentation process, then productivity is improved, but segmentation boundaries become unstable due to frequent insignificant data changes
Solution Approach 1:
The system performs preliminary actions by establishing segmentation boundaries based on significant strategic factors first, then uses tactical adjustments for routine updates. This preliminary strategic segmentation framework prevents frequent insignificant changes from disrupting the overall segmentation structure, while still allowing efficient tactical updates when needed.
Solution Approach 2:
The system implements dynamics by allowing segmentation boundaries to be flexible at the tactical level while maintaining stability at the strategic level. Tactical segments can adjust to data changes within predefined ranges, but significant strategic boundaries remain stable unless major market shifts occur, resolving the contradiction between stability and adaptability.
2Measurement precision
If manual segmentation is performed, then segmentation accuracy is improved, but the process becomes complex and time-consuming
Solution Approach 1:
The system divides the segmentation process into distinct strategic and tactical segments. Strategic segmentation handles high-level market divisions with greater accuracy focus, while tactical segmentation handles operational adjustments. This segmentation of the segmentation process maintains accuracy while reducing overall complexity through automated workflows.
Solution Approach 2:
The system introduces an intermediary automated segmentation engine that bridges manual strategic decisions and automated tactical adjustments. This intermediary processes data, identifies patterns, and suggests segmentation boundaries, reducing the complexity of manual segmentation while preserving accuracy through human-in-the-loop validation for strategic decisions.
3Adaptability or versatility
If frequent segmentation updates are made to reflect data changes, then adaptability is improved, but lead time for understanding segmentation increases
Solution Approach 1:
The system implements periodic action by scheduling strategic segmentation reviews at fixed intervals rather than continuously updating based on every data change. Tactical updates occur periodically at predetermined frequencies. This periodic approach maintains adaptability to significant changes while preventing unnecessary updates that would increase planner lead time and cause confusion.
Solution Approach 2:
The system changes parameters by implementing threshold-based updates where segmentation boundaries only change when data changes exceed predefined significance thresholds. This parameter change approach allows the system to be adaptable to meaningful market shifts while ignoring insignificant fluctuations, thereby reducing the frequency of updates and planner lead time.
Data Source
AI summary
A system and method for performing strategic segmentation including a supply chain network having a strategic segmentation planner, an inventory system, a transportation network and supply chain entities. The strategic segmentation planner includes a computer having a memory and a processor, that selects a workflow depth including an amount of data to analyze, discovers features by analyzing cleansed data to locate features which are characterized by features data, pre-processes the features data to standardize the features data, performs multi-dimension segmentation by computing feature importance to generate multi-dimensional segments, assigns policy parameters to the supply chain network based on the generated multi-dimensional segments, and trains a machine learning model by applying a cyclic boosting process to the standardized features data wherein the cyclic boosting process iteratively learns relationships associated with the generated multi-dimensional segments.