AI BriefingMarket Kurly news
The latest AI and developer news from Market Kurly, with short summaries.
Visit website →Hibernate's Time Runs Backwards
Analyzed and resolved a login error caused by a nanosecond-handling bug in Hibernate that occurred during a Spring Boot 3.x upgrade.
Kelly Builds Digital Twin-Based Simulation of Logistics Center Picking Process
Kelly used an AnyLogic-based digital twin to simulate the picking process and verify the effects of optimizing worker paths and inventory placement.
Kurly Automates Review Curation with LLM and Chain of Thought… Achieves Accuracy Without ML Models
Kurly unveiled a method that uses LLM and Chain of Thought techniques to accurately and transparently curate unstructured review data without an existing ML model.
Kurly Boosts 'No-Result Search' Revenue by Over 300% with Vertex AI Search Adoption
Kurly adopted Google Vertex AI Search to resolve typo and synonym issues, improving purchase conversion by over 300% in no-result (NR) search cases.
Kurly Shares Case of Automating Review Analysis by Calling Gemini Pro from BigQuery
Kurly automated review summarization and analysis by calling Gemini Pro directly from BigQuery, without building a separate model.
Kurly Migrates Airflow Operations to Kubernetes… Achieves 50% Cost Reduction and Stability
Kurly migrated its Airflow operating environment to Kubernetes, cutting costs by 50% and resolving GitSync and OOM issues.
Root Cause Analysis of Data Lookup Failure Due to Unrefreshed Snapshot in MariaDB Aurora Mode
The overlap between MariaDB Connector/J's Aurora mode and the open-in-view setting caused the Master DB's Snapshot to not be refreshed, resulting in data not being retrievable, and this was resolved.
Kurly Builds Real-Time Serving Architecture for Cart Recommendation Service Based on TorchServe
Kurly's Data Service Development Team built a zero-downtime real-time serving system for its cart recommendation model through TorchServe tuning and GracefulShutdown implementation.
Kurly boosts conversion rate by about 100% with cart complementary product recommendations
Kurly introduced a complementary-product recommendation model for the shopping cart, raising conversion rate and purchase amount by about 100%.
Kurly Overcomes Deep Learning Limitations... Unveils Laplacian Filter-Based Blurry Image Detection Technology
Kurly acknowledged the limitations of CNN models and improved blurry image detection accuracy using a rule-based algorithm based on the Laplacian filter.
Kurly Drives Up Membership Sign-up Rate by Introducing Motion to Quick Menu Icons
Kurly introduced motion to its quick menu icons and verified an increase in Kurly Members sign-up rate.
Kurly Reassigns Delivery Zones with OR-Tools-Based Combinatorial Optimization… Cuts Delivery Time by 5%
Kurly revealed a method that solves the TC-zone assignment problem with an OR-Tools-based combinatorial optimization model to minimize delivery time.
Kurly Developer Overcomes Limitations of JPA saveAll: Improving 1:N Data Performance with JDBC Bulk Insert
A Kurly developer pointed out the inefficiency of JPA saveAll and improved 1:N data processing performance using JDBC Bulk Insert leveraging Auto Increment PK inference.
Kurly Log Team Resets Product Roadmap After Interviewing 29 Customers at Food Festa
The Kurly Log team interviewed 29 customers at the Kurly Food Festa, confirmed low awareness, and rebuilt its second-half roadmap.
Kurly Shares 'Divide and Conquer' Strategy and One Team Collaboration Case in BeautyKurly Expansion
In expanding BeautyKurly, Kurly launched features in stages using a divide-and-conquer strategy and strengthened One Team collaboration.
Kurly Developers Introduce Kurly Culture Through Self-Purchased Product Recommendations
Kurly developers shared self-purchased ('naedon-naesan') product recommendations by category—housewarming, dieting, and coding snacks—along with the culture of using Kurly in-house.
Kurly Resolves Concurrency Issues in Inbound Service with Redisson-Based Distributed Locks
Kurly used Redisson and AOP to resolve concurrency issues in its inbound service and ensure data consistency.
Hey Joyce Builds In-House Webinar System with AWS IVS and Sendbird
Hey Joyce built its own webinar system using AWS IVS and Sendbird in just 2 weeks and has run it more than 200 times.
Kurly Unveils UX Design and Operational Results of Beauty Personalization Service 'My Kurly Style'
Kurly's Product Design team shared the step-by-step/list-type UX design strategy and 8 months of operational performance for its beauty personalization service 'My Kurly Style'.
Beauty Kurly Improves Filter UX and Optimizes API Calls by Adopting React Query
Beauty Kurly switched from Redux to React Query, improving the average product selection position when applying filters from 32nd to 19th.