Shopper Supply Prediction via ML Selection Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional online concierge systems underestimate the available number of shoppers by failing to account for their capacity to fulfill more orders than received during a time interval, leading to inefficiencies in order fulfillment.
Innovation Solution
The online concierge system trains a selection prediction model to determine the predicted time for shoppers to select orders based on a shopper-order ratio value, generated from the number of orders and available shoppers, allowing for more accurate allocation of shoppers during time intervals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional online concierge systems measure shopper output based on observed amounts of time shoppers work when fulfilling orders, then the measurement is simple and direct, but the available number of shoppers is underestimated because the system fails to account for shoppers having capacity to fulfill more orders than received during a time interval
Solution Approach 1:
The patent changes the measurement parameter from observed work time to predicted work capacity by introducing a machine learning model that predicts the amount of time shoppers would work to fulfill a predicted number of orders. This transforms the measurement from a simple observational metric to a predictive metric that accounts for shopper capacity beyond actual order volume.
Solution Approach 2:
The system performs preliminary prediction of shopper availability by using a machine learning model to forecast how much time shoppers would work during a time interval before actually assigning orders. This preliminary action allows the system to plan order allocation more accurately by knowing the predicted shopper capacity in advance.
2Productivity
If the system uses predicted number of orders to determine shopper allocation, then order fulfillment capacity is optimized, but the complexity of predicting and allocating shoppers increases
Solution Approach 1:
The machine learning model automatically predicts shopper availability and the system automatically adjusts shopper allocation based on these predictions, reducing the need for manual intervention. The system serves itself by using the predicted data to make allocation decisions without requiring complex manual planning or external inputs.
Solution Approach 2:
The system uses feedback from the machine learning model's predictions about shopper capacity to continuously adjust and optimize order allocation. The predicted amount of time shoppers would work feeds back into the allocation system, creating a closed-loop optimization process that improves productivity while managing complexity through automated feedback mechanisms.
Data Source
AI summary
An online concierge system assigns shoppers to fulfill orders from users. To allocate shoppers, the online concierge system predicts future supply and demand for the shoppers' services for different time windows. To forecast a supply of shoppers, the online concierge system trains a machine learning model that estimates future supply based on access to a shopper mobile application through which the shoppers obtain new assignments by shoppers. The online concierge system also forecasts future orders. The online concierge system estimates a supply gap in a future time period by selecting a target time to accept for shoppers to accept orders and determining a corresponding ratio of number of shoppers and number of orders. The online concierge system may adjust a number of shoppers allocated to the future time period to achieve the determined ratio number of shoppers and number of orders.