Search Result Page Optimization

Search Result Page Optimization

Making search more intent-aware and discovery more efficient

Making search more intent-aware and discovery more efficient

#SearchExperience #AIIntegration #ProductOptimization

Role:

Product Designer

Company:

Pinkoi

Year:

2026

Platform:

Desktop Web · Mobile Web · iOS · Android

Desktop Web · Mobile Web · iOS · Android

01

OVERVIEW

Aligning search results with shopping intent

The Search Results Page is an important entry point for product discovery and organic traffic at Pinkoi. However, the search experience still had challenges. Search results didn't always match users' shopping intent, and fixed filters couldn't support different shopping needs.

To address these challenges, I proposed two design strategies: Visual Search Refinement and a two-level filtering experience. Visual suggestions helped users find more relevant product categories, while I designed a more intuitive two-level filtering interface using the dynamic product filters developed by the engineering team. Together, these improvements helped users explore products and narrow down search results more easily.

After launch, we observed improvements in product discovery and shopping behavior. On Mobile Web, the product view rate increased from 37.4% to 44.7%. In the updated iPhone and Android apps, the add-to-cart rate increased by an average of approximately 13.5% compared with the previous versions.

The Visual Search Refinement feature I proposed also showed promising results. On Web, users who interacted with this feature had a roughly 30% higher product view rate than those who didn't. While this comparison doesn't establish a direct causal effect, it provides early support for using visual suggestions to guide product discovery.

The Search Results Page is an important entry point for product discovery and organic traffic at Pinkoi. However, the search experience still had challenges. Search results didn't always match users' shopping intent, and fixed filters couldn't support different shopping needs.

To address these challenges, I proposed two design strategies: Visual Search Refinement and a two-level filtering experience. Visual suggestions helped users find more relevant product categories, while I designed a more intuitive two-level filtering interface using the dynamic product filters developed by the engineering team. Together, these improvements helped users explore products and narrow down search results more easily.

After launch, we observed improvements in product discovery and shopping behavior. On Mobile Web, the product view rate increased from 37.4% to 44.7%. In the updated iPhone and Android apps, the add-to-cart rate increased by an average of approximately 13.5% compared with the previous versions.

The Visual Search Refinement feature I proposed also showed promising results. On Web, users who interacted with this feature had a roughly 30% higher product view rate than those who didn't. While this comparison doesn't establish a direct causal effect, it provides early support for using visual suggestions to guide product discovery.

OUTCOMES

+20%
Product view rate
Mobile Web product view rate after search rose from 37.4% to 44.7%, a 7.3-point increase (about 19.6% relative).
+20%
Product view rate
Mobile Web product view rate after search rose from 37.4% to 44.7%, a 7.3-point increase (about 19.6% relative).
+20%
Product view rate
Mobile Web product view rate after search rose from 37.4% to 44.7%, a 7.3-point increase (about 19.6% relative).
+28%
Mobile Web Add-to-cart rate
Mobile Web add-to-cart rate per search session rose about 28% year over year.
+28%
Mobile Web Add-to-cart rate
Mobile Web add-to-cart rate per search session rose about 28% year over year.
+28%
Mobile Web Add-to-cart rate
Mobile Web add-to-cart rate per search session rose about 28% year over year.
+14%
App Add-to-cart rate
Add-to-cart rate on the new iPhone and Android versions was about 13.5% higher than on the previous versions.
+14%
App Add-to-cart rate
Add-to-cart rate on the new iPhone and Android versions was about 13.5% higher than on the previous versions.
+14%
App Add-to-cart rate
Add-to-cart rate on the new iPhone and Android versions was about 13.5% higher than on the previous versions.
+30%
Visual Search Refinement
Web users who clicked it later viewed products about 30% more often than those who didn't. Click-through rate was about 12%.
+30%
Visual Search Refinement
Web users who clicked it later viewed products about 30% more often than those who didn't. Click-through rate was about 12%.
+30%
Visual Search Refinement
Web users who clicked it later viewed products about 30% more often than those who didn't. Click-through rate was about 12%.

02

CHALLENGE

More Search Results ≠ Finding the Right Products

01

Search Terms Don't Always Reflect Users' Shopping Intent

Search Terms Don't Always Reflect Users' Shopping Intent

Users may not know the exact product name or may search with broad terms. As a result, search results may not match their actual shopping needs, making it difficult to find the products they're looking for.

02

Irrelevant Search Suggestions Limit Further Exploration

Irrelevant Search Suggestions Limit Further Exploration

Existing search suggestions aren't always relevant to users' search terms. Some are repetitive or too similar, making it difficult for users to refine their searches or explore related products.

03

Fixed Filters Don't Adapt to Different Shopping Needs

Fixed Filters Don't Adapt to Different Shopping Needs

Different products have different shopping criteria, such as material, capacity, or intended use. However, fixed filters don't adapt to the search context, making it harder for users to narrow down their results.

Design Challenge

Balancing Product Discovery and Business Value

Balancing Product Discovery and Business Value

The search results page is more than a product list. It's also an important entry point connecting users' shopping needs with business opportunities. The challenge was to balance product discovery, shopping criteria, featured services, and commercial exposure within limited screen space.

03

GOAL

Help people find the right product faster

01

Improve search relevance

Improve search relevance

Bring results closer to what people are actually searching for.

02

Improve discovery and filtering efficiency

Improve discovery and filtering efficiency

Help users explore related products and narrow down results with more relevant search suggestions and filters.

04

STRATEGY

Different search intents need different ways to explore

People don't always know what they want to buy at the start. Searching "matcha" may still be about browsing product types; searching "water bottle" often means comparing specifics like capacity and material.

So I proposed two design strategies to support different search needs.

Strategy 01

Visual Search Refinement

Visual Search Refinement

When intent is still forming

Intuitive images and category entry points help people recognize product types quickly and find their next direction to explore.

Strategy 02

Dynamic Facets

Dynamic Facets

When intent is specific

Combining the search keyword with product attributes, filters adapt to the search context and surface the information that matters for the decision.

05

DESIGN

Key design decisions

01

Help Vague Searches Find a Direction

Help Vague Searches Find a Direction

Based on user research and search data, we found that users often searched with broad keywords, making it difficult to narrow down their results.

To address this, I designed visual search suggestions that combine images and text, helping users explore relevant product categories and find a clearer direction.

For example, when searching for gifts, users could quickly explore categories like birthday gifts, gifts for women, or Christmas gifts without repeatedly changing their search keywords.

Supporting Search Guidance Beyond the Top of the Page

I also introduced related search suggestions within the product grid and at the bottom of the page, extending search guidance beyond the initial entry point.

By integrating these suggestions into the browsing experience, users could refine their searches and discover more relevant products without starting over.

Related Searches in the Product Grid

Integrated related search suggestions into the product grid, allowing users to discover alternative search directions while browsing.

Related Search Keywords at the Bottom

Added related keywords at the bottom of the page, giving users another opportunity to refine their searches and continue exploring.

02

Let Filters Adapt to the Shopping Context

Let Filters Adapt to the Shopping Context

Different products require different filters, but the previous experience showed the same filtering options for every search.

To address this, I redesigned the filtering experience across devices, incorporating dynamic filters based on search keywords and product attributes.

On mobile, I designed a two-row layout. The first row displayed basic filters, while the second showed relevant product attributes based on search keywords.

On desktop, dynamic filters were integrated into the left sidebar, allowing users to refine their results while browsing.

I also collaborated with the PM, AI, Localization, and Business teams to review the recommended attributes and ensure they aligned with real shopping needs.

03

Create Commercial Value Without Crowding Discovery

Create Commercial Value Without Crowding Discovery

One of the business requirements was to create more opportunities for brand advertising on the search results page.

I noticed unused space beside the product grid on desktop, so I proposed placing ads there without taking up the main product browsing area.

This approach created additional advertising opportunities while maintaining a balance between product discovery and business goals.

06

OUTCOME

Positive shifts in search exploration and shopping behavior

Positive shifts in search exploration and shopping behavior

PRODUCT IMPACT

+20%
Product view rate
Mobile Web product view rate after search rose from 37.4% to 44.7%, a 7.3-point increase (about 19.6% relative).
+20%
Product view rate
Mobile Web product view rate after search rose from 37.4% to 44.7%, a 7.3-point increase (about 19.6% relative).
+20%
Product view rate
Mobile Web product view rate after search rose from 37.4% to 44.7%, a 7.3-point increase (about 19.6% relative).
+28%
Mobile Web Add-to-cart rate
Mobile Web add-to-cart rate per search session rose about 28% year over year.
+28%
Mobile Web Add-to-cart rate
Mobile Web add-to-cart rate per search session rose about 28% year over year.
+28%
Mobile Web Add-to-cart rate
Mobile Web add-to-cart rate per search session rose about 28% year over year.
+14%
App Add-to-cart rate
Add-to-cart rate on the new iPhone and Android versions was about 13.5% higher than on the previous versions.
+14%
App Add-to-cart rate
Add-to-cart rate on the new iPhone and Android versions was about 13.5% higher than on the previous versions.
+14%
App Add-to-cart rate
Add-to-cart rate on the new iPhone and Android versions was about 13.5% higher than on the previous versions.
+30%
Visual Search Refinement
Web users who clicked it later viewed products about 30% more often than those who didn't. Click-through rate was about 12%.
+30%
Visual Search Refinement
Web users who clicked it later viewed products about 30% more often than those who didn't. Click-through rate was about 12%.
+30%
Visual Search Refinement
Web users who clicked it later viewed products about 30% more often than those who didn't. Click-through rate was about 12%.

KEY FINDINGS

CONCLUSION

01

Mobile Web: Encouraging More Users to Explore Products

Mobile Web: Encouraging More Users to Explore Products

Following the redesign, the product view rate on Mobile Web increased from 37.4% to 44.7%, while the add-to-cart rate per search session increased by 28%.

Funnel analysis showed that most of the improvement occurred between search results and product pages, with more users moving from search to product exploration.

Following the redesign, the product view rate on Mobile Web increased from 37.4% to 44.7%, while the add-to-cart rate per search session increased by 28%.

Funnel analysis showed that most of the improvement occurred between search results and product pages, with more users moving from search to product exploration.

02

App: Bringing Users Closer to Purchase Decisions

App: Bringing Users Closer to Purchase Decisions

On App, product view rates remained relatively stable between the previous and updated versions, while add-to-cart rates per search session increased by approximately 15% on iPhone and 12% on Android.

Unlike Mobile Web, the improvements were concentrated after product views, with users showing a higher likelihood of taking the next shopping action.

On App, product view rates remained relatively stable between the previous and updated versions, while add-to-cart rates per search session increased by approximately 15% on iPhone and 12% on Android.

Unlike Mobile Web, the improvements were concentrated after product views, with users showing a higher likelihood of taking the next shopping action.

03

Visual Search Refinement: Helping Users Find a Clearer Direction

Visual Search Refinement: Helping Users Find a Clearer Direction

Visual Search Refinement appeared in approximately 15–20% of searches, achieving a 12% click-through rate on Desktop Web, nearly twice that of other platforms. This suggests stronger engagement with search guidance on Desktop Web.

Across all four platforms, users who clicked visual search suggestions had product view rates 8–16 percentage points higher than those who did not. These findings suggest that visual search guidance goes beyond offering additional search options, with the potential to help users narrow down their search and continue exploring products.

07

TAKEAWAYS

Rethinking how search results help people choose

01

Knowing What to Buy Doesn't Mean Knowing How to Search

Knowing What to Buy Doesn't Mean Knowing How to Search

Even when users know what they want to buy, they may not know which keywords to use. This project reinforced my belief that a good search experience should not only provide relevant results but also help users find the right direction.

02

Using Data to Guide the Next Iteration

Using Data to Guide the Next Iteration

The initial usage of Dynamic Facets was low, so we need to better understand how often the feature appears, how often users engage with it after seeing it, and how usage differs across App versions.

The initial usage of Dynamic Facets was low, so we need to better understand how often the feature appears, how often users engage with it after seeing it, and how usage differs across App versions.

Based on these findings, we could explore two improvements:

• Expand feature coverage: Make dynamic filters available for more search terms.

• Improve filter visibility: Make the filter entry point easier to discover and use.

Contact

I don’t just design products.
I help shape what’s next.

I enjoy turning complexity into clarity,
connecting user needs with business goals,
and helping teams build products that make a difference.

Contact

I don’t just design products.
I help shape what’s next.

I enjoy turning complexity into clarity, connecting user needs with business goals, and helping teams build products that make a difference.

© 2026 Lian Yeh

Based in Taiwan · Open to global opportunities

© 2026 Lian Yeh

Based in Taiwan · Open to global opportunities