use cases

How e-Commerce Players Can Improve Product Discovery with On-site Voice Search

Otto Söderlund

Feb 19, 2021

4 min read

Designing voice-first applications requires new approaches to UX and UI design. In this post, we'll go through some best practices for designing voice-driven user interfaces.

  • Copy link

  • Mail

  • LinkedIn

  • Facebook

  • Twitter

Success in eCommerce requires that your customers not only find what they are looking for but also find products that they didn't know they need. Good search is the key in both scenarios.

Slow product discovery is one of the top frustrations for ecommerce shoppers

Some customers enter your store knowing exactly what they are looking for, whereas others only have a vague idea of what they want and need some inspiration. In traditional knowledge management terms this is referred to as findability and discoverability.

In e-commerce context findability refers to the ease of finding a specific product that the customer is looking for, whereas discoverability refers to the ease of finding potential product alternatives meeting a more vague idea of the need. Why is this important? Because to simplify, e-commerce shoppers have two modes that they are on while shopping, which both need to be catered in an optimal way.

JourneyUser taskBuying behaviorTime spent
Product DiscoveryLook for ideas and alternativesImpulsive, opportunisticMore
Deal FindingLook for best deal (price, availability, delivery time)Rational, effectiveLess

TABLE: Typical journeys that e-commerce shoppers are on while looking for products.

In Journey 1, customers are browsing and want to see as relevant options as effectively as possible. They have not yet made the final buying decision, but might act impulsively. In Journey 2, customers have already made the buying decision and are really looking for the place where they can get the specific product as cheap and fast as possible.

Ensuring that customers find the right products to fit their needs from your catalog as effectively as possible is a top priority for e-commerce merchants and relevant for both Journeys. As a matter of fact, according to studies the slowness of finding the right product is one of the top frustrations for ecommerce shoppers.

“32% of UK shoppers feel that it takes a long time to find what you want”

The dominant product discovery method, product search combined with filters, is major driver of churn

Search alone is a powerful tool if the user knows exactly what they want (Journey 2), but if they are still considering the options (Journey 1), their search terms would by definition be more vague resulting in a large set of search varying results.

So ecommerce merchants have added filters to allow users to better refine the search results of these more vague searches. This is the most common approach for product discovery and most modern online stores use it. However according to Forrester bad product search experience still accounts for 68% of churn, so something must be broken.

Let's go through the most common product search usability problems in touch screen and web applications.

Product search problem #1: Too many filters

Screenshot of a eCommerce store with too many search filters

Illustration of an online store that has thirty filters

If the product search has too many search filters, user will have problems browsing through them, even if they can all be relevant. In addition, users might be looking for these filters with different names which means they have problems finding the correct filter even if the store had them.

Product search problem #2: Too many filter values

Scnreenshot of an ecommerce store with too many search filter values

Illustration of an online store filter, where there are so many values that the filter requires a separate own search box within the filter

Sometimes the search filters itself have too many values and selecting the correct one becomes tedious. For example, let's suppose the user can select a color as a search filter. On the other hand, adding all possible colors can help the user find the exact color they are looking for but on the other hand, finding the correct shade of blue becomes difficult.

Hence, there's a balance between adding more filter values for more granular search or removing filter values for simplified search.

Product search problem #3: Confusing categorization

Screenshot of confusing search categories

Illustration of confusing categories

Sometimes categories itself can be confusing because of naming conventions or other issues. In the example, there are too many brands for the search to be effective. Sometimes the problem is synonyms and naming.

For instance, should a user find USB memory sticks under category "Storage", "Memory", "Accessories" or maybe "Other"?

Voice search and filtering can radically improve the product discovery experience

There must be a better way. What if instead of pointing, clicking and writing, users could just say what they are looking for? And immediately see the results updated in real time in front of their eyes. And what if correcting or changing your mind would be easy and smooth? Here’s a demo of how that can work in practice:

Using voice to complement visual product browsing makes discovery significantly easier, faster and more enjoyable. Users get less frustrated and browse through more products. Voice powered product discovery and search experience can help e-commerce players improve their conversion and retention, and differentiate from their competitors.

One clear benefit of voice search is that it supports synonyms and different ways of expressing the same thing naturally and intuitively. There's no need to give a single name for a category, but the same category can have many names.

If the user is looking for "pants", but the designer has named this category "trousers", voice search can support both names. Typical graphical user interface can't support both, because this would lead to our problem #2 - too many filter values.

If you want to learn more about voice-enabled product search and filtering, contact us! You can find more cool examples of voice user interfaces here.

About Speechly

Speechly is a YC backed company building tools for speech recognition and natural language understanding. Speechly offers flexible deployment options (cloud, on-premise, and on-device), super accurate custom models for any domain, privacy and scalability for hundreds of thousands of hours of audio.

Latest blog posts

company news

Speechly is joining Roblox

Hannes Heikinheimo

Sep 19, 2023

1 min read

voice tech

4 Voice Chat Solutions for Virtual Reality

Voice chat has become an expected feature in virtual reality (VR) experiences. However, there are important factors to consider when picking the best solution to power your experience. This post will compare the pros and cons of the 4 leading VR voice chat solutions to help you make the best selection possible for your game or social experience.

Matt Durgavich

Jul 06, 2023

5 min read

company news

Speechly Has Received SOC 2 Type II Certification

Speechly has recently received SOC 2 Type II certification. This certification demonstrates Speechly's unwavering commitment to maintaining robust security controls and protecting client data.

Markus Lång

Jun 01, 2023

1 min read