Kesko Senukai Digital Improves CTR From Site Search by 47%

About Kesko Senukai Digital

Kesko Senukai Digital (KSD) is an eCommerce company, operating online stores in Lithuania, Latvia, Estonia. They are part of Kesko Senukai Lithuania, which develops retail store chains in Baltics and Belarus.

Senukai is a well-known brand in Baltics for almost 30 years. They launched their first e-store back in 2009. Since then, the store has grown significantly, offering over 200,000 products assortment for its customers today. In 2018, Kesko Senukai Digital acquired online trading group 1A, which operates online stores in Lithuania, Latvia, and Estonia. With this acquisition, the company ensures that customers can choose from a broader range of products.

They use SearchNode in 6 different e-stores (www.senukai.lt, www.ksenukai.lv, www.k-rauta.ee, www.1a.lt, www.1a.lv, www.1a.ee) in 4 languages (Lithuanian, Estonian, Latvian, Russian).

Results From Site Search On Senukai.lt

Immediate Conversion Growth

• • Back in 2019, one year after effortless and fast implementation of SearchNode, KSD observed how their CTR from sessions with search skyrocketed by 47%, compared with previous search solution.

• • Other metrics kept growing as well. For instance,  add-to-cart YOY rate from site search grew by 22%.

• • The company continues enjoying the fruits of advanced site search and continually sees the growing results, which is made possible due to the continuous search improvements process utilized by SearchNode.

Pandemic Related Growth In Results

• • In 2020 Senukai.lt saw even better results from their search. Due to the COVID-19 pandemic, they had to close brick-and-mortar locations, which led to overall growth in sessions, while sessions with site search grew by +86% YOY.

• • As SearchNode provides scalable solutions and reacts fast to any changes that occur, it was extremely helpful for the company to deal with the increased traffic load and ease visitors’ discovery process.  Sessions with site search brought the company +56% YOY conversion rates growth.

Challenges

Before SearchNode, Kesko Senukai Digital was trying to build their search in-house, using open source Elasticsearch technology. They had one part-time developer, working on their site search.

They managed to build only a very simple site search, with basic functionality. Their search solution was not proactively assisting users, often returning irrelevant and inaccurate results. This resulted in low search usage and poor conversion rates.

What is more, the only people who were able to work with the site search were engineers. There was no simplified solution, which could be used by their merchandising team and product owner.

The company realized that this is not working for them and that they need to revolutionize their site search ASAP.

Looking for solution

KSD started to look at what’s out there in the site search market. The first option they considered was to continue improving their current search, built on Elastic. The second option was to choose one of the usual SaaS providers, such as Algolia and others. The third option was SearchNode – a hybrid solution between SaaS and consulting partner.

1. In-House Elasticsearch Development
After careful research, the company decided to remove the first option from consideration. KSD realized that to have an experienced full-time Elasticsearch team of 3-6 people, is expensive, and time-consuming. What is more, from their own experience, they knew that to build sophisticated site search solution with advanced features is not as easy as it can look at the beginning.

2. SaaS Vendors
Moving on, Kesko Senukai Digital also refused the offers of various SaaS providers. The company wanted to have autonomy over their search product, and they had highly advanced requirements for its search solution. After talking with some providers, and analyzing their capabilities, KSD learned that these solutions have loads of limitations buried in their APIs, and cannot fulfill their needs properly. The company didn’t want to be dependent on product roadmaps and wait for the new features to be introduced to the global product. They also didn’t want to put their people to the boring position of merely putting synonyms and redirects in the dashboard that comes with SaaS solution providers.

3. Hybrid: SaaS + Search Experts
As for the third option, Kesko Senukai Digital decided that it’s the perfect solution for them, as they got not only a good search product but experienced search engineers and consultants as well. We also provided an opportunity to have search engineers on-demand, which was relevant for the company, as they were going through a load of changes in terms of product supply, as they were acquiring other eCommerce companies.

 

“We had rather frustrating experience developing site search ourselves with Elastic. After evaluating all the options on the table, we realized that SearchNode is a perfect solution for us. We wanted to have automated solution that does not require manual work, with sophisticated search functionality while still remaining autonomous. SearchNode and their team offered all that and delivered terrific results for our business. ”

Justinas Lukaševičius
Chief Technology Officer

The implementation of SearchNode

As with all of our clients, SearchNode implementation was organized in such a way that KSD needed to devote its least possible development effort.

The main task of the Kesko Senukai Digital search team was to communicate and discuss with SearchNode goals and features of the site search to make sure that it fits business objectives and priorities, and to provide feedback during the implementation process. From the technical point of view, they only needed to provide data export API according to our requirements. SearchNode did all the rest – from data analysis/optimization and tracking scripts to the creation of search user interface and custom AI algorithms.

The full cutting edge search solution was launched in seven weeks from the initial kick-off workshop. Our search experts keep working together with KSD as an integral part of their search team, operating as if the company would have internal search engineers, to ensure even better results.

Later one, SearchNode was also launched on the newly acquired 1A websites (www.1a.lt, www.1a.lv, www.1a.ee).

Solutions created for KSD

Relevant search results

Data Relevance Algorithms

SearchNode provided Kesko Senukai Digital with our powerful AI search platform, with industry-leading site search features. But reaching the next stage of relevant search experience demands more than just an excellent and versatile search product, which is why our search engineers dived deep into analyzing KSD product data and user behavior. Examination allowed us to come up with data-driven insights, and create custom algorithms, explicitly designed for KSD on top of AI-based SearchNode search platform.

As we keep on working together with the company on their search improvements, SearchNode solution engineers keep developing and advancing these custom algorithms, which leads to scalable site search improvements. The SearchNode unique approach of linking AI search platform with Kesko Senukai Digital specific algorithms allow the company to have a genuinely relevant search, optimized for business goals no matter the setting.

Natural Language Processing

KSD needed a sophisticated search solution, to properly process four languages, in which they offer their assortment: Lithuanian, Latvian, Estonian, and Russian. We implemented custom stemming and natural language processing (NLP) algorithms, based on the specifics and grammar rules of these languages, to create more accurate and intuitive search. SearchNode algorithms, with the support from AI, helped process words written in any form, and understand the context of user queries better and return the most relevant results at any given time. This helped to lift Kesko Senukai Digital search relevance significantly, resulting in improved conversion rates.

Personalized Shopping Experiences

Personalization is another powerful tool that we implemented for Kesko Senukai Digital. We integrated the SearchNode search platform with the leading personalization tool BitREC. This helped Kesko Senukai Digital in creating more intimate experiences based on a user’s browsing history. Personalization solutions implemented by us automatically recognize customer buying intent, boost shopper engagement, and drive sales.

“Good experience both as a search engine and with the custom search improvement tasks. SearchNode delivered us with excellent search products, which have the right features and automation to deliver results. The dedicated search team is easy to work with and fast to respond to support tasks and create tailored solutions on demand. We don’t need to have a team for onsite search, rather a product prepared by field experts to personalize.”

Justinas Lukaševičius
Chief Technology Officer

Continuous Search Improvements

Just as with all other clients of ours, search improvements don’t end with search solutions going live on KSD e-stores. Our search experts team keep proactively working as part of the eCommerce search team in the company, striving to make the site search better each day. With Kesko Senukai Digital, we have one sprint of continuous search improvements each month, which is divided into two parts.

1st Part: Ongoing Search Maintenance

We dedicate some portion of the time to keep everything working intact. During this part, our search engineers make sure that all of the data is being renewed promptly, and all of the bugs are being fixed immediately. Likewise, they apportion some time to implement UI changes and carry out any unexpected or urgent tasks.

TYPES OF FIX

• • Synonyms

• • Quick fixes

• • Minor UI changes

• • Promotions, landing pages, redirections

• • Product priority adjustments

ROLES

• • Both: KSD team or SearchNode team

GOAL

• • To quickly fix individual cases

IMPACT TO SEARCH METRICS

• • No significant improvement

 

2nd Part: Scalable Search Improvements

This part is committed to creating new search functionality or implementing new search features. Each month search teams from SearchNode and Kesko Senukai Digital create a list of hypotheses for search improvements. KSD product owner manages and prioritizes this list to select what should be tested. Then SearchNode engineers create the test, and we observe which of the variations is performing better and act accordingly.

TYPES OF FIX

• • Relevance algorithm improvements (fixing a pattern of issues)

• • Ranking strategy improvements

• • Merchandising automation

• • New search features

• • User behavior analysis

• • A/B testing

ROLES

• • KSD manages priorities and sets goals

• • SearchNode helps to identify nonperforming areas and raise hypotheses

• • SearchNode carries the implementation

GOAL

• • Making impactful search improvements

• • Reducing the need for manual work

IMPACT TO SEARCH METRICS

• • Search metrics rise over time

 

Continuous Search Improvements Preserves Growth

Continuous improvement process ensures that the search is always optimized to achieve the best possible business results for the Kesko Senukai Digital , and best search experience for its clients. As we continue working together with the company as one team, the site search is continuously improved in the most scalable and efficient way.  In each new sprint, SearchNode engineers develop custom algorithms specific only to KSD case. Thus, we enrich our AI-based search platform with custom algorithms, which maximizes Kesko Senukai Digital site search potential and company revenues.