Outbound Forecasting Simulation for Fulfillment Center SKU Allocation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional systems for outbound forecasting are difficult, time-consuming, and inaccurate due to the need for manual modification and repeated testing of parameters, and they lack the ability to perform 'what if' analysis, especially for entities with multiple fulfillment centers and do not consider events like unexpected increases in customer demand.

Innovation Solution

A computer-implemented system that uses a simulation algorithm to generate a fulfillment center (FC) priority filter, optimizing the allocation of SKUs among FCs by calculating outbound capacity utilization values and modifying allocations based on simulated customer demand and constraints such as maximum capacities and transfer costs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual modification and repeated testing of parameters is performed, then routing optimization can be achieved, but the process becomes time-consuming and difficult

Engineering Contradiction:

Improverouting optimizationVSAvoidtime-consuming process

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs automated simulation and optimization without requiring manual parameter modification. The simulation algorithm automatically tests different routing scenarios and generates optimized routing plans, eliminating the need for manual repeated testing while maintaining optimization quality

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical processes (manual parameter modification and testing) with automated computational simulation. The simulation algorithm computationally models different routing scenarios and automatically determines optimal routes, substituting human manual work with automated software-based simulation

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If simulation is performed on a larger scale rather than granular scale, then processing efficiency improves, but accuracy decreases

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidforecasting accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system segments the simulation process to operate at multiple levels: it can perform granular simulations for specific fulfillment centers or product categories when detailed accuracy is needed, and aggregate simulations across the entire network when overall planning is required. This segmentation allows the system to adapt the level of detail to match the specific planning needs, maintaining both efficiency and accuracy where required

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The simulation algorithm allows dynamic adjustment of granularity parameters. Users can modify parameters such as the level of detail (SKU-level vs. category-level), time horizon, and geographic scope to balance processing efficiency with forecasting accuracy based on specific business requirements

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If conventional forecasting systems are used, then basic routing can be maintained, but the ability to perform 'what if' analysis is lost

Engineering Contradiction:

Improvebasic routing maintenanceVSAvoidwhat if analysis capability

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The simulation system is designed to be dynamic and adaptable. It can easily modify input parameters to represent different scenarios (such as demand changes, capacity constraints, or new routing options) and immediately simulate the effects. This dynamic capability enables comprehensive 'what if' analysis while maintaining ease of operation through a user-friendly interface that allows simple scenario definition

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11657412B2Systems and methods for outbound forecasting based on a fulfillment center priority value

Publication Date: 2023.05.23 COUPANG CORP

AI summary

The embodiments of the present disclosure provide systems and methods for outbound forecasting, comprising receiving an initial distribution of priority values to each fulfillment center (FC) in each region, running a simulation, using a simulation algorithm, of the initial distribution, calculating an outbound capacity utilization value of each FC, determining a number of FCs comprising an outbound capacity utilization value that exceeds a predetermined threshold, feeding the simulation algorithm with the determined number of FCs to generate one or more additional distributions of priority values, generating a FC priority filter comprising an optimal set of priority values based on the one or more additional distributions of priority values, and modifying an allocation of a plurality of SKUs among a plurality of FCs based on the generated FC priority filter.