Forrester Wave™ Q3, 2023 Recognizes Netcore Unbxd as a Leader Learn more
Nov 27 2017

Machine learning versus automation in site search for ecommerce

Pavan Sondur

CEO & Co Founder


Once upon a time, in the land of online commerce, a great debate raged: machine learning or automation? Which was the better solution for site search? Well, let's start by defining our terms.

Machine learning is artificial intelligence that allows computer systems to learn and improve from data without being explicitly programmed. It's like giving a computer a set of rules and then letting it figure out the rest on its own.

On the other hand, deep learning is a subfield of machine learning that involves training artificial neural networks on massive amounts of data. These networks can then make decisions and predictions based on that data, just like a human brain.

Now, let's talk about site search. When you go to an online store and type in a search query, the results that come back are determined by an algorithm. If that algorithm is based on machine learning, it means that it's constantly learning and improving based on the data it receives. This can lead to more accurate and relevant search results over time.

On the other hand, an automation-based site search relies on predefined rules and logic to return results. While this can still be effective, it may not be as flexible or adaptable as a machine learning-based solution.

Machine Learning Site Search Vs. Automation Site Search

Though the terms automation and machine learning are used interchangeably, the most significant difference is that automation does not require any teaching. Automation is the process of using machines to automate what humans would otherwise do manually. 

For instance, in eCommerce Site-Search, a successful automation-based solution will use past purchase information to rank products with high sales numbers at the top. It might even use 'clicks' to automate showing highly viewed products at the top. It is advantageous because many search systems today require humans to input rules to boost the products' rank to the topmost position. 

The flip side of automation is that it can go wrong with ranking within search results. If a 'legging' is selling well, it's great if it shows up when somebody searches for 'pants.' The system is geared towards ranking the most popular products to be shown the most. What about the 80%+ visitors who want to see pants, not just the most popular legging (which technically is also a pant)? It ends up catering to the top 20% of best-selling products to 20% of visitors shopping online. 

If you need a system that not only automates human tasks but also sifts through a lot of data to identify patterns of predictability in data sets, you need Machine Learning. 

What is Machine Learning?

Machine Learning systems require intensive computations (a lot of CPUs) and need training data sets — a lot of data. They will use that to predict, for instance, the likelihood of a user clicking on a particular type of product after a specific search. 

Another use case would be to predict what other queries are similar to one specific query with different search results. The limiting factor for machine learning is the data — the more data it ingests, the more likely outcomes will be realistic. Machine learning models cannot predict outside of the tabulated data that is fed in. 

It is important — If somebody is offering machine learning and is not ingesting a HUGE amount of data, they are just automating; there is no machine learning in play. In a typical use case of well trained and excellent-performing machine learning system, it ingests data sources like:

  1. The source of traffic
  2.  Search queries
  3. Clicks on filters
  4. Clicks rank of products
  5. Product clicks
  6. Time spent on PDP pages
  7. Add-to-cart events
  8. Purchases
  9. Exits
  10. Repeat visits
  11. Non-search clickstream events
  12. Web-based social trending data

While relevancy plays its part with machine learning, it can determine that there is a sufficient deviation in behavior when people search for ‘pants’ v/s ‘leggings’ independently. It’s not programmed or automated, as is evident in the image above.

How is machine learning site search leveraged for eCommerce?

While relevancy plays its part with machine learning, it can determine that there is a sufficient deviation in behavior when people independently search for 'pants' v/s 'leggings.' It's not programmed or automated, as is evident in the image above.

How is machine learning site search leveraged for eCommerce?

At Unbxd, when we compared a machine learning site search system (CTRs and conversion rates) on an A/B test with the best-automated systems, they both behaved similarly on the top 5% of queries. 

However, the Machine Learning site search outperformed automated search by 2x (100% difference in conversions) with the rest 95%. It is because sales data heavily drive the top 5% of search queries. The remaining 95% of questions need more predictability — not just automation. 

One thing to note, though, is to be realistic about what machine learning can deliver. You need significant data to make training models work. If your site has less traffic — it might take a while before it starts kicking in. To summarize, you can use this simple checklist to verify if a site search has machine learning:

  1. Does the site search ingest at least five different types of signals?
  2. What machine learning models does it use?
  3. What are some patterns that these models have predicted?
  4. Is there a dedicated data sciences team?
  5. What's the technical architecture for machine learning in play?

Book a demo to know how Unbxd's ML Algorithm can help better your site search experience! 


More To Explore
Grow your business
Schedule a Demo
Find out how Netcore Unbxd can help you uplift on-site conversions
Talk to a PIM expert
Find out how Netcore Unbxd can help you uplift on-site conversions