Online Concierge Order Allocation via Shopper Availability Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional online concierge systems face challenges in efficiently fulfilling orders due to intermittent availability of shoppers and time windows, leading to decreased user likelihood in placing orders.
Innovation Solution
The online concierge system maintains discrete time intervals for order fulfillment, estimates the number of available shoppers using a trained machine learned model, and allocates a specified percentage of shoppers per time interval, allowing for flexible order fulfillment by authorizing delivery at any time prior to the selected discrete time interval.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If a specific amount of estimated shoppers is allocated for fulfilling orders during scheduled time windows, then the system can maintain resources to more rapidly fulfill short-term orders, but significant increases in order volume occupy the allocated shoppers, limiting time windows for order fulfillment
Solution Approach 1:
The system dynamically adjusts shopper allocation based on real-time order volume and shopper availability. Instead of fixed allocation, the system continuously monitors order intake rates and shopper completion rates, reallocating shoppers between scheduled and unscheduled orders to adapt to changing conditions, thereby maintaining both rapid fulfillment capability and flexibility for new orders
Solution Approach 2:
The system changes the parameter of shopper allocation from a static predetermined amount to a dynamic variable that adjusts based on order volume, shopper availability, and time window constraints. This allows the system to optimize fulfillment speed while maintaining adaptability to varying order volumes by continuously adjusting allocation parameters
2Quantity of substance
If the amount of estimated shoppers available for fulfilling orders within a specific time window is increased, then more orders can be received, but significant increases in order volume quickly occupy the shoppers, decreasing likelihoods of users subsequently placing orders
Solution Approach 1:
The system implements feedback loops that monitor order fulfillment rates, shopper availability, and user ordering patterns. When shopper occupancy reaches certain thresholds or fulfillment delays occur, the system adjusts allocation strategies and notifies users of updated availability, creating a feedback mechanism that maintains reliability by preventing over-allocation while maximizing utilization
Solution Approach 2:
The system performs preliminary actions by pre-allocating shoppers to scheduled orders while maintaining a reserve pool for unscheduled orders. This preliminary allocation strategy ensures that users can place orders with confidence that shoppers will be available, while the reserve pool prevents complete occupancy, maintaining system reliability for subsequent orders
Data Source
AI summary
An online concierge system receives two types of orders, one of which requires fulfillment in a specific time interval, while the other can be fulfilled anytime up to a specific time interval. A machine learning model, trained on historical data about available shoppers in discrete time intervals, is used to predict how many shoppers will be available to fulfill orders in each time interval. For each time interval, the system retrieves the relevant orders of both types and creates candidate groups including orders of both types. For each group, the system determines a fulfillment cost based on items in the orders. The candidate group with the lowest cost is selected, and the orders in the selected group are sent to devices of available shoppers in that interval, prompting the shoppers to view and fulfill the orders.