E-commerce Shopping Cart Prediction Engine for Response Time Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional e-commerce platforms face performance issues, particularly in updating electronic shopping carts, which leads to delays as the number of items increases, resulting in computational complexity and potential cart abandonment.
Innovation Solution
Implementing a shopping cart prediction engine that generates and caches predicted electronic shopping carts with pre-computed promotions and price totals, allowing for asynchronous computation and reduced response time when the e-shopper interacts with their cart.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If shopping cart computations are performed in real-time when e-shoppers interact with their carts, then computational accuracy is maintained, but response time increases and delays occur especially as cart size increases
Solution Approach 1:
The system performs preliminary actions by predicting future shopping cart states and pre-computing the associated computations (promotions, pricing, taxes) before the e-shopper actually adds items to the cart. This allows the system to have computations ready in advance, eliminating the need for time-consuming real-time computation when the cart is updated.
Solution Approach 2:
The system dynamically adjusts computation strategy based on predicted cart states. Instead of a static real-time computation approach, the system uses machine learning models to predict which cart modifications are most likely and pre-computes only those scenarios, making the computational process adaptive and efficient.
2Loss of time
If shopping cart computations are pre-computed and cached for predicted carts, then response time is reduced, but computational resources are consumed in advance
Solution Approach 1:
The system applies partial action by pre-computing only a subset of possible shopping cart states - specifically those predicted by machine learning models to be most likely. Rather than pre-computing all possible cart combinations (excessive action), the system focuses computational resources on the most probable scenarios, reducing overall resource consumption while maintaining performance benefits.
Solution Approach 2:
The system uses feedback from e-shopper behavior patterns and historical data to refine its predictions of future cart states. This feedback loop allows the system to continuously improve its prediction accuracy and optimize which computations to pre-cache, ensuring computational resources are used efficiently based on actual usage patterns.
3Ease of operation
If the system waits for e-shoppers to add items to cart before computing promotions and pricing, then computational resources are conserved, but user experience deteriorates due to delays
Solution Approach 1:
The system performs preliminary computations for predicted shopping cart states before the e-shopper actually completes the add-to-cart action. By anticipating future cart contents based on browsing behavior and historical data, the system prepares pricing, promotions, and tax calculations in advance, so that when the user does add items, the information is already ready and displayed instantly.
4Reliability
If shopping cart computations are re-computed every time cart contents change, then computational accuracy is maintained, but system performance deteriorates with larger cart sizes
Solution Approach 1:
The system performs preliminary computations for predicted future cart states, storing these pre-computed results for later retrieval. When actual cart modifications occur, the system checks whether the new cart state matches any previously predicted and computed states, allowing it to retrieve pre-computed accurate results rather than re-computing, thus maintaining reliability while improving performance.
Data Source
AI summary
Embodiments provide systems, methods, and computer storage media for prediction and computation of electronic shopping carts. In an example embodiment, for each interaction between an e-shopper and an e-commerce application, one or more predicted electronic shopping carts that represent a combination of items the e-shopper is likely to purchase are generated based on current items in the e-shopper's electronic shopping cart and recent interactions with the e-shopper. For some or all of the predicted electronic shopping carts (e.g., those with top predicted confidence levels), corresponding shopping cart computations (e.g., identifying application promotions, determining a price total for the items in the predicted shopping cart) are executed and cached prior to the e-shopping adding the predicted items. As such, a page configured to visualize the predicted electronic shopping cart with a value retrieved from the cached shopping cart computations (e.g., price total for the predicted electronic shopping cart) is generated.