UI Logic Improvement and Onboarding Enhancement

• Implemented UI logic to restrict side-panel openings to a single action per click, reducing accidental triggers by 75% across 10+ modules.
• Added priority-based log filtering capable of processing over 12,000 entries per minute, cutting average debugging time by 50%.
• Enhanced onboarding flow by hiding the 'I already have a server' button for 95% of first-time users, decreasing setup errors by 35%.
• Resolved a PC-specific page-update failure affecting 100% of Windows users, restoring full functionality.
• Standardized FAB icon dimensions to 48×48 px across 8 Brand Hero pages, achieving 100% visual consistency.

• Scaled the product from concept to 1M+ registrations, 60K DAU, and 20K MAU in 12 months.

• Managed a cross-functional team of 30+ (Dev, DevOps, GameDesign), introduced Agile workflows and CI/CD improvements.

• Increased average session time by 500% (10 mins → 1 hour) through game balance redesign and reward system revamp (ABC tests).

• Reduced churn rate by 15% using CJM-based onboarding, tracked with Hotjar and Amplitude.

• Localised the product into 8 languages, forming partnerships with local KOLs based on GEO analytics.

Goal: Increase revenue by 2x in 12 months. Initiatives: Identified key metrics that are important for revenue. Clustered and segmented users. Established conversions that need to be monitored daily. Worked with data team to build monetization dashboards. Defined and owned the strategy and execution of changes to be made in monetization. Results: Revenue increased by 2.5x in 12 months. Conclusion: The key to success was identifying the right metrics to track, clustering and segmenting users, and establishing daily monitoring of conversions.

Tackled the learning issue by implementing various personalized learning styles and improved the product checkout process by decreasing the clicks required for payment from 4 to 2 through A/B testing. This streamlined the checkout process, making it more efficient and user-friendly.

As a computer vision expert, I was consulted to address the challenge of facial pore recognition for a beauty application. The problem involved accurately identifying and measuring individual pores on various skin types and tones. To tackle this, I designed an algorithm that could adaptively capture high-resolution images and extract relevant features. Leveraging machine learning, I trained a model on a comprehensive dataset that I helped gather, comprising different face images under various lighting conditions. The resulting algorithm could recognize and measure individual pores with high precision, providing personalized skincare recommendations to users, and thereby enhancing the app's user experience.