Search by Algolia
Haystack EU 2023: Learnings and reflections from our team
ai

Haystack EU 2023: Learnings and reflections from our team

If you have built search experiences, you know creating a great search experience is a never ending process: the data ...

Paul-Louis Nech

Senior ML Engineer

What is k-means clustering? An introduction
product

What is k-means clustering? An introduction

Just as with a school kid who’s left unsupervised when their teacher steps outside to deal with a distraction ...

Catherine Dee

Search and Discovery writer

Feature Spotlight: Synonyms
product

Feature Spotlight: Synonyms

Back in May 2014, we added support for synonyms inside Algolia. We took our time to really nail the details ...

Jaden Baptista

Technical Writer

Feature Spotlight: Query Rules
product

Feature Spotlight: Query Rules

You’re running an ecommerce site for an electronics retailer, and you’re seeing in your analytics that users keep ...

Jaden Baptista

Technical Writer

An introduction to transformer models in neural networks and machine learning
ai

An introduction to transformer models in neural networks and machine learning

What do OpenAI and DeepMind have in common? Give up? These innovative organizations both utilize technology known as transformer models ...

Vincent Caruana

Sr. SEO Web Digital Marketing Manager

What’s the secret of online merchandise management? Giving store merchandisers the right tools
e-commerce

What’s the secret of online merchandise management? Giving store merchandisers the right tools

As a successful in-store boutique manager in 1994, you might have had your merchandisers adorn your street-facing storefront ...

Catherine Dee

Search and Discovery writer

New features and capabilities in Algolia InstantSearch
engineering

New features and capabilities in Algolia InstantSearch

At Algolia, our business is more than search and discovery, it’s the continuous improvement of site search. If you ...

Haroen Viaene

JavaScript Library Developer

Feature Spotlight: Analytics
product

Feature Spotlight: Analytics

Analytics brings math and data into the otherwise very subjective world of ecommerce. It helps companies quantify how well their ...

Jaden Baptista

Technical Writer

What is clustering?
ai

What is clustering?

Amid all the momentous developments in the generative AI data space, are you a data scientist struggling to make sense ...

Vincent Caruana

Sr. SEO Web Digital Marketing Manager

What is a vector database?
product

What is a vector database?

Fashion ideas for guest aunt informal summer wedding Funny movie to get my bored high-schoolers off their addictive gaming ...

Vincent Caruana

Sr. SEO Web Digital Marketing Manager

Unlock the power of image-based recommendation with Algolia’s LookingSimilar
engineering

Unlock the power of image-based recommendation with Algolia’s LookingSimilar

Imagine you're visiting an online art gallery and a specific painting catches your eye. You'd like to find ...

Raed Chammam

Senior Software Engineer

Empowering Change: Algolia's Global Giving Days Impact Report
algolia

Empowering Change: Algolia's Global Giving Days Impact Report

At Algolia, our commitment to making a positive impact extends far beyond the digital landscape. We believe in the power ...

Amy Ciba

Senior Manager, People Success

Retail personalization: Give your ecommerce customers the tailored shopping experiences they expect and deserve
e-commerce

Retail personalization: Give your ecommerce customers the tailored shopping experiences they expect and deserve

In today’s post-pandemic-yet-still-super-competitive retail landscape, gaining, keeping, and converting ecommerce customers is no easy ...

Vincent Caruana

Sr. SEO Web Digital Marketing Manager

Algolia x eTail | A busy few days in Boston
algolia

Algolia x eTail | A busy few days in Boston

There are few atmospheres as unique as that of a conference exhibit hall: the air always filled with an indescribable ...

Marissa Wharton

Marketing Content Manager

What are vectors and how do they apply to machine learning?
ai

What are vectors and how do they apply to machine learning?

To consider the question of what vectors are, it helps to be a mathematician, or at least someone who’s ...

Catherine Dee

Search and Discovery writer

Why imports are important in JS
engineering

Why imports are important in JS

My first foray into programming was writing Python on a Raspberry Pi to flicker some LED lights — it wasn’t ...

Jaden Baptista

Technical Writer

What is ecommerce? The complete guide
e-commerce

What is ecommerce? The complete guide

How well do you know the world of modern ecommerce?  With retail ecommerce sales having exceeded $5.7 trillion worldwide ...

Vincent Caruana

Sr. SEO Web Digital Marketing Manager

Data is king: The role of data capture and integrity in embracing AI
ai

Data is king: The role of data capture and integrity in embracing AI

In a world of artificial intelligence (AI), data serves as the foundation for machine learning (ML) models to identify trends ...

Alexandra Anghel

Director of AI Engineering

Looking for something?

facebookfacebooklinkedinlinkedintwittertwittermailmail

User-generated content is the new and rapidly growing trend in the ecommerce industry. Social commerce combines social media and ecommerce platforms to provide customers with highly personalized and precisely targeted online product discovery process and shopping experiences. Live Streaming product reviews are taking the ecommerce world by storm and boosting engagement, sales, average cart volume, and speed of online purchasing. 

Marketplaces are undeniably leading in the adoption of these new innovative practices. Many times they face unique challenges, rarely affecting typical ecommerce retailers, such as managing extremely large catalogs, dealing with high product variety, managing customer experience, and supplier relationships simultaneously. All these aspects require creative approaches to product discovery. On top of the typical marketplace challenges listed above, C2C marketplaces stand out in their unique ecommerce operational needs and business model requirements.

Let’s consider the following analogy: think of an online marketplace as a giant warehouse. Millions of products from thousands of categories all under the same roof. Without proper organization, the customer will quickly get lost and overwhelmed with the amount of offerings available. The suppliers are also not going to be satisfied, since customers will not be able to find their products in the warehouse, they will inevitably give up the search attempts fairly quickly and go shop in a different, better organized store. You can now see that just like the warehouse, a C2C marketplace is balancing between producing higher conversions for sellers and optimizing product discovery for buyers. Let’s try to identify the challenges C2C platforms face and find effective and actionable solutions for each of them.

Optimizing product and content discovery for C2C marketplaces

Catalog management

Seller acquisition

In the early stages of a marketplace, it’s highest priority is to have products to sell. Companies like eBay, Amazon, Etsy, and Airbnb, to name a few, didn’t become go-to ecommerce platforms because they had a good relevance and product discovery from day one; instead, they became market leaders because they had a wide range of products others weren’t able to offer. Nowadays, new entrants have to compete against established players by acquiring more users and content than their competitors.

How do C2C marketplaces attract sellers? 

Make it easy for sellers to list their products. It’s safe to assume that a typical seller will cross-post their products on multiple C2C sites and platforms. The easier it is to list and sell products on your C2C marketplaces, the higher the chances of sellers choosing your platform over competitors. The downside of this seller acquisition strategy is poor data hygiene. What this means is that by not collecting enough information about the items sold on your marketplace, you end up having low quality data, which affects the buyers on your marketplace. Once you reach a critical mass of sellers on your C2C marketplace, your next step should be to improve the data quality. 

  • Listing data quality – ensuring that the sellers provide adequate information about the product
  • Seller quality – ensure the transaction security and build trust in transacting on the platform by minimizing fraud, transaction disputes, and low vendor responsiveness levels.

Driving high conversion rates

At some point, a C2C marketplace will need to manage the buyer behavior. As your online marketplace evolves, the C2C business goals switch from offering sellers an easy-to-list platform to generating a high checkout conversion rate from buyers. To achieve this goal successfully, it is vital to present the correct item in front of a customer at the right time. Such precise relevancy requires accurate listing data from the sellers – a good data hygiene. 

Undoubtedly, such shifts in the product listing requirements will result in a loss of a seller’s segment in the short term. Once the C2C transaction conversion rates on the marketplace improve, the existing sellers will prefer to stay on the platform, potentially attracting the previously lost sellers back. An additional benefit of this strategy change is driving buyer retention, by gaining the reputation of a trusted marketplace for a chosen demographic segment.

Implementation

Accuracy of data retrieval for online search and navigation

Search and Navigation is, at its core, data retrieval. To improve accuracy, C2C marketplace needs to make sure every listing on the platform can be easily identified by its data. For that purpose, relying on free text entered by sellers will not be a usable solution. A set of clear, uniform identifiers has to be used across the entire catalogue to generate accurate and precise data retrieval processes.

Having a clean complete data model is key for textual relevance & category accuracy. Textual relevance means that the buyers will see relevant search results to their queries. Category accuracy refers to having products assigned to the correct categories. For instance, when searching for a “red top”, we would like to see search results with red blouses, red t-shirts, but not blue tops (textual relevance) and also not red sneakers (category accuracy). However, relying on sellers’ honesty when following the product listing process is not necessarily an optimal approach. To ensure that sellers play by the rules, one of the possible solutions for C2C Marketplaces can be to implement powerful ranking strategy functionality. 

Motivating sellers to improve their listings

When a seller lists a product on a C2C marketplace, the position at which their item appears on the category page or a search results page directly correlates to the frequency and speed at which their item sells. The position of the item on the list is decided by the ranking algorithm. Having products listed in the top row vs the bottom of the page has a huge impact on the seller’s revenue. In a sea of similar items, standing out is key. The speed at which the item sells is also critical, as freshness is an important factor in buyers decisions when shopping on C2C marketplaces.  

The ranking algorithm gives C2C marketplaces a powerful tool to motivate sellers to improve their listings and act ethically on the platform. Transparency is an important element to keep in mind when communicating changes on the marketplace platform to the sellers. To establish a healthy win-win relationship with C2C marketplace vendors, a clear communication of the ranking algorithms, platform practices and expectations regarding business transactions should be communicated consistently to the sellers. When thinking about ranking, marketplaces need to consider the following elements:

  • Seller quality
  • Listing quality
  • Item quality
  • Adding business rules

Seller quality

A higher rated seller is beneficial for the buyer shopping experience and satisfaction on the platform, higher sales and conversions, and brand loyalty. Seller quality can be ranked based on the following criteria:

  • Transaction dispute rate: high dispute rate or long response time will bury the results featuring the seller, while low dispute rate and short response time will boost the results.
  • User/buyer feedback: higher ratings will boost the results, while lower ratings will bury them.
  • Time on platform: trusted sellers with more tenure on a platform will get ranked higher in the results than newer and less established sellers.
  • Response time to messages: shorter response time will boost the results, while longer response time will bury them.

Listing quality

A higher listing quality improves the relevance and accuracy of the results presented to buyers. It increases the buyer satisfaction, seller conversion rates, marketplace margins, and brand loyalty. When incentivizing the sellers to list products accurately, the listing quality can be rated based on the following elements:

  • Percentage (%) of fields filled out by the seller
  • Listings containing an image (should be ranked higher)
  • User feedback (e.g., likes, add to cart actions)

Item rank

The elements to consider when ranking a product listing on the marketplace:

  • Conversion rate of items in the same category / brand / sub category / similar items
  • Views statistics: average number of seconds/minutes spent by the buyers viewing the item, time of the day and days of the week when the item was viewed the most
  • Time until the auction ends, in case the auctioned listing has an expiration date
  • Transaction information: sold items should not appear at the top of the page

Adding business rules

Newness and availability are highly important metrics for a C2C marketplace. The ranking algorithm needs to consider the following aspects:

  • Item’s freshness: when it was listed on the platform
  • Item’s availability: are the items in stock and how many are available at the moment

Monetizing search and discovery

In addition to the ranking strategy discussed above, C2C marketplaces can leverage their internal business data insights, advanced merchandising tools, and AI capabilities to optimize the monetization of search and discovery. 

Custom ranking

Custom ranking allows companies to incorporate business data into the relevance algorithm to customize it for their unique business needs and industry specifics. For example, the results can be ranked by popularity, profit margins, views, or ratings. For B2C marketplaces, seller ranking, buyer likes, and similar ratings serve an important role in the ranking strategy.

There are several strategies available for setting up custom ranking. The choice of the strategy that will fit each company’s business needs depends on how often the data changes and how many pieces of data there are.  

  • Reducing precision in custom ranking values
    • If you want to take multiple custom ranking attributes into consideration in order to get a good mix of results, you need to reduce the precision of this attribute or the other attributes may never be used. 
    • Learn more about reducing precision in custom ranking values in this blog.
  • Embedding business logic in the custom ranking. Examples include:
    • Ranking based on brand: “myBrand: true”
    • Ranking based on category: “organic: true”
    • Ranking based on stock availability: “inStock: true”
    • Ranking based on sales margin: $56 (3), $55 (10), $54 (12) 
    • Ranking based on internal popularity metrics: sold_past_month, sold_past_week

https://www.algolia.com/doc/guides/managing-results/must-do/custom-ranking/

User Centric / Contextual Ranking

This step includes a powerful and impactful element in your relevance strategy: Personalization. The Personalization tool organizes results based on every tracked action from a specific user. Once the user logs-in to their account, Personalization kicks in and suggests personalized results specific to each unique user’s preferences and behavior. Personalization strengthens interactive search by adding a personal layer to the relevance strategy. Adding personalized preferences to the search experience makes results more engaging for individual users.

 

 

 

Search and Category Page merchandising

For C2C marketplaces, it is common to automate merchandising on search and category pages. It is typical for ecommerce marketplaces to maintain extremely large catalogs of products, making it not feasible to manually apply merchandising strategy to each product. While automation provides an efficient solution, there are situations where manual merchandising is able to deliver extra value and optimize the overall user experience on the platform.

Search Merchandising ensures that all the necessary business logic is incorporated in the search results that will be presented to the user. There are multiple complementary ways to design an effective strategy for any eCommerce business, such as:

  • Merchandise popular searches and trending content for seasonal promotions and items
  • Merchandise empty queries and no results stats as well as federated search
  • Pin, hide, boost, and bury search results
  • Redirect searches and show promotional banners in search results

Category Merchandising workflow enables companies to apply business logic to the category pages. This way, every time a shopper is browsing the website and different product categories, the results will appear in a specific order that can be easily adjusted according to the current promotional business needs.

  • Pin, hide, boost, and bury categories
  • Add content carousels to category landing pages
  • Add dynamic landing pages

 

 

 

AI synonyms suggestion

Advanced AI algorithms generate dynamic synonyms suggestions based on users’ searches. Enabling synonyms suggestions helps with product discoverability and shortens the search duration. This is especially critical for the ecommerce industry and marketplaces in particular. For large catalogs containing millions of products, with thousands of sellers and buyers active on the platform, it is safe to assume that different terms will be used for the same products. Manually curating synonyms is not feasible in this case; therefore, to improve product discovery and monetization on the platform, AI algorithms should be applied.

 

 

 

Recommendations

Recommendations are ideal to encourage users to discover more of your catalog based on what they’re already interested in. 

  • Frequently Bought Together: recommends items that are often bought together. For a given item, it recommends a list of items based on the conversion events your users perform on your platform.
  • Related Products: recommends items that are related to each other. For a given item, it returns a list of items based on the clicks and conversion events your users perform on your platform.

Conclusion

C2C ecommerce marketplaces represent a blend between user-generated content and an ecommerce marketplace platform. Leading C2C marketplaces are aiming at building a community and encouraging sellers and entrepreneurs to act as influencers on the platform. With the social commerce trend taking the world by storm, C2C marketplace businesses face unique challenges in their efforts to attract quality sellers, improve product discovery, and optimize the conversions on their platforms and online stores. 

The solutions to the common marketplace challenges, featuring user-generated content, include efficient catalog management, C2C specific implementation steps, and monetization strategies that leverage advanced relevance and merchandising tools to optimize search and discovery of products on the C2C marketplaces.

About the author
Tanya Herman

Product Manager

Recommended Articles

Powered byAlgolia Algolia Recommend

10 features of the best online marketplaces
e-commerce

Catherine Dee

Search and Discovery writer

How to design your merchandising (and searchandising) stategies for success
e-commerce

Peter Villani

Sr. Tech & Business Writer

What are marketplace platforms and software? Why are they important?
e-commerce

Vincent Caruana

Sr. SEO Web Digital Marketing Manager