Tag: search


Spell check, Auto Correct, Error Tolerance – How important is it for Site Search at your Magento store?

Posted on November 22, 2017 by


Any Search product for e-commerce at a bare minimum will provide an autocorrect or spell check feature, even though they do not provide analytics to determine what is trending at your store. Is it because Spelling correction is more important that data analytics of your search data? Absolutely not.

Purpose of Spell check

Like a human, a spell check feature is enabled to ensure that when a visitor types/asks for an erroneous search term (Chrestmas, Skerts, Phenes) or a correct search term (Chrestmas, Skirts, Phones), the search engine shows them the same results.

Hygiene factors

Like any product you purchase, there are certain bare minimum requirements for a Search product to qualify as one. Spelling correction is one of them, along with features like keyword stemming, Dynamic Filters and Live Catalog Updates. We call them hygiene factors, cause as retailers you would have thought about these requirements and would have integrated the same if your time permitted at the least amount of time & cost. You should not pay extra, just for these features in a Search product.

Development effort

If you are a small e-commerce store, you can integrate an open source spell check library readily available online, to meet these hygiene factors. At Tagalys we do not boast about our spell check feature, cause it is very subjective to determine how much of revenue increased at our customers, because of a spelling correction.  We also feel that with the predictive suggestions, we provide in our search product, it leaves little room for error, as visitors tend to choose from suggestions than type a full search term. We also feel that customers who want to use Tagalys ONLY for our spell check feature, are probably early in their journey as online retailers, not understanding that spell check will not change their bottom line.

Business Impact

We have read from sources on how spell check has to potential to increase revenue up to $3M. This might be a bit stretched. This is because of a few reasons,

  1. Less than 2% of overall search terms require a spell check
  2. Many “No results” pages happen as visitors search for compounded words as separate words e.g., Mens Wear, Polka Dot, Strap Less etc., No spell check library in the world including that of Amazon.com, can detect and convert search results for compounded & uncompounded words into the same search results. There are other ways to address this and spell check is not one of them.
  3. In order for a Spell check engine to add $3M in revenue, you have to assume the visitors who made the spelling mistake will not buy or search again for the same term in the correct spelling. Then, you need to have around 600K searches with typos a month, converting at 5% with $100 per transaction, to hit this mark. This also means that assuming 2% of your search terms are erroneous, you will need to have close to 30M searches a month for this benefit to be worth $3M.

Verdict

Spell check is a hygiene factor for the search product at your e-commerce store. It should NOT be a show stopper or a key decision influencer, If you are anywhere near the 1m searches a month, your decision on a good search product should be around how it analyzes data & how the analysis of search data can improve search conversion.

You can learn more about Search from Tagalys at https://www.tagalys.com/products/e-commerce-site-search/

Posted in eCommerce Site Search

Relevance only ecommerce Site Search is passé. Increase revenue with Intelligent Search results

Posted on October 30, 2017 by


Humans have the attention span of a gold fish

Or less. Time Magazine & Microsoft reported in May 2015, that “The average attention span for the notoriously ill-focused goldfish is nine seconds, but according to a new study from Microsoft Corp., people now generally lose concentration after eight seconds, highlighting the affects of an increasingly digitalized lifestyle on the brain.” If this is the state of online visitors, you need to think before deciding what products to show your visitors, cause they will lose interest in 8 seconds and you will lose a sale.

Get Smart

Site search is a high value funnel for online visitors. Visitors who search are more likely to convert to customers than those who browse. Then why is your site search engine, dumb? Yes, you read that right, if you have a site search engine that spits out all products just because it matches the query (keyword relevance), your search engine is not thinking and you are losing on revenue.

Get Tagalys

Search engines like Algolia, Swifttype and others, are known for very fast search results. But what is the point in ecommerce, when you have 8 seconds to help your visitors find something of interest? Take a search query like “Dresses” or “Sofas”, these generic searches will contribute to over 605 of your search volume and each of these searches will results in over 100 products per query. What do you show? These queries are driven from mobile devices and now, you have only 2 products per scroll. Thats over 50 scrolls to see all the products in for that query.

This is why you need Tagalys, to analyze data, learn from it and predict what products are most likely to sell for that query. Show results for any search query, where products are sorted by the probability of sale. Tagalys Search also offers other value added services like Search suggestions, Popular Searches, Pinned Searches, Merchandising, but the core of what we do is determine sort orders for products to ensure what shows on top has a higher probability of sale.

Tagalys also applies the same data driven approach across all our API’s so you can ensure your visitors engage with the products that are most likely going to bring you a customer. We apply our data driven approach across Site Search, Product Recommendations & Product Listing pages. If you want to go one step further, we also apply personalization, which is the ability to understand what products are most likely going to appeal to each unique visitor.

Signup for a 28 day free trial and find out for your self. No credit card required. Let the numbers speak for itself.

 

Posted in e-Commerce General e-Commerce Personalization eCommerce Site Search

Magento 1 & 2: Increase ecommerce SEO traffic using Intelligent Product Listing pages

Posted on October 25, 2017 by


High-value organic traffic at any e-commerce store is the most efficient way to reduce customer acquisition costs. This improves your path to profitability. At Tagalys, many of our clients use Intelligent Product Listing pages and get the added benefit of ranking high on search results for keywords that are on these product listing pages.

What was most fascinating is that the keywords on these product listing pages showed in the top 5 SERP results consistently across all clients. So we did some research on clients to see common factors that led to ranking high on SERP. We also noticed that clients, whose Tagalys powered product listing pages ranked high on SEO, also had an SEO expert adding the right elements on these pages directly and ensuring the pages were listed on the site map and on a landing page. The reason why there were listed on the sitemap, landing page or anchored on the home page, was to have a search engine bot, index this page, collecting all the details, thus allowing it to calculate a relevancy score for the keywords mentioned on the product listing page.

Before we get into the details, here is a brief video on Intelligent Product Listing pages

The below elements are features available in Intelligent Product Listing pages which can be directly utilized without having to add details to your e-commerce platform

Bounce rate: Probably the most important metric that helps sustain & improve the SERP ranking of a product listing page but often overlooked. In order for bounce rates to be low, organic visitors need to visit another page like a product page or another listing page once they view your product listing page that showed in SERP. You need to know what products to showcase, to want your visitors to click on them. Most online stores, spend time on the SEO hygiene factors that we list below but do not have any idea what products to showcase on the page. They tend to sort them by some basic sort orders like new arrivals, most popular, best sellers without understanding or evaluating if this sort order will lead to high CTR from the product listing page to the product page itself. This sort order is the core competency of Tagalys, as our TRENDING sort order, orders products on the page by calculating the probability of sale, based on the historical data of how visitors are engaging with products at your store.

From a search engines standpoint, high bounce means the traffic it sends does not find the page interesting thus to protect itself, it will start removing your page from the SERP to show other pages that have lower bounce rates.

Page Title: Always have your search keyword as part of the page title starting with a verb e.g., Buy Maxi Dresses between $999 and $1499, Shop Diamond Rings with Rubies etc., Visitors seeking to visit an e-commerce store are more likely to use a verb in their query vs. a visitor seeking to know more about content sites.

Url component: Having the search keywords as part of your URL also helps increase the relevance of the product listing page to be found in the search index. Keyword density and availability of the keywords closer to the domain name in the URL are critical in the relevance index for search engines

Page Heading: Not always required, but helps with SEO, to further re-enforce the keyword relevance in the product listing page, leading to better ranking on SERP.

Description: It is important to have a specific description of a page and not a catch-all, as that can lead to higher bounce rates which also affects your SERP ranking. For example, if your product listing page is about Maxi dresses, ensure the description talks about the maxi dresses and not what it can be paired with like peep toe shoes, pearl jewelry etc., This is because if a visitor searching for pearl jewelry stumbles upon your page for maxi dresses since “pearl jewelry” as it was in the description, they will leave the page thus increase the page bounce rate. This low conversion metric, reduces the rank of the page thus limiting visibility in future organic search results.

Meta keywords & Meta Description: While there is some value in having these fields with relevant keywords, we have seen that they do not play a significant role in SERP rankings. If you have good content listed in the title, URL & description, it would be sufficient for meeting high relevance scores for the search keywords in question.

All of the above variables can be easily entered & edited by e-commerce teams, without having to modify this on the backend of your platform.

Domain ranking: All of the above works well, assuming your domain has higher authority in the SEO world. For this, search engines like google report on a domain score that looks at variables like your page load time, mobile friendliness, 404 redirects, etc., Hence if this basic hygiene is not met by your store, that could lead to a lower score on SERP, as your domain is ranked low by the search engine.

Watch our demo site to learn more or schedule a 1:1 demo with us at your convenience. What are you waiting for? Contact us now or start your 28-day free trial immediately. You can also read more at Intelligent Product Listing pages.

Posted in e-Commerce Product Listing pages

Semantic search for ecommerce site search – do you need it?

Posted on January 19, 2017 by


Semantic search as per Wikipedia seeks to improve search accuracy by understanding the searcher’s intent and the contextual meaning of terms as they appear in the searchable database, whether on the Web or within a closed system, to generate more relevant results.

Some of the examples of how this may translate in ecommerce site search for a fashion retailer are, search queries that read like “Dresses for spring” or “Best selling moccasins in 2016 April” or ” Trendiest shirt for a cocktail  party”. You get the drift. So will it make an impact on your conversion rate, if your search engine has the potential to show accurate search results to these search queries

  1. Data: In our cumulative analysis of search query data across clients across verticals, less than 0.07%, meaning 7 out of 10000 search queries, were semantic in nature. Semantic search becomes relevant if the revenue generated from the x% who convert from the 0.07% is considered as significant to your business and also offsets the increase in cost for this added ability . Even sites like Amazon, Walmart and Target where 1% of their search volume could lead to millions of search queries, do not place a heavy emphasis on Semantic search for many reasons. Some of which could be ROI, customer experience or latency in the display of search results, that could increase search bounce rate. Convinced and want to  SIGNUP NOW?semanticwalmarttarget
  2. Frictionless experience: As suggested in our article best practises in site search, consumers expect to be fed. They are spoilt and prefer to have predictive suggestions that match intent, hence almost 99.07% of your audience is more likely to click on a suggestion or type a short query, vs. a fully type a semantic query. If you notice a trend on certain contextual search queries or terms (e.g., cheap, under, newest etc.,) from the database, that can be managed without a semantic system, but creating a rule set or synonyms libraries to tell your search index what products are potentially relevant for that query.amazon ss target ss walmart ss
  3. Consumer search behaviour: When it comes to visitors who choose the search funnel, most of them already show intent or interest in purchase. Hence search queries are typically tied to products (dresses, shoes, beds etc.,) or combinations of products and tags (Maxi dress, Nike Shoes, Single beds etc.,).
  4. Vertical: Semantic search is usually more common in a contextual database vs. a product database. Most visitors who visit your online store are looking to buy products. And unless you are selling something that is not easily understood to the end customer, most of your visitors know what to search for
  5. Performance vs Price: Lets say that over 1% of your search volume consists of queries that are semantic in nature and you need a site search engine to deliver results. As a product manager this leads to leveraging an NLP system than can process or cache results for a semantic query in less than 50 ms. Anything longer than that, is going to slow your results page and that can lead to bad search experience. Secondly, there is an increase in cost to build an maintain a system that can not only process these queries with accurate results, but also show these results to your visitors like any other search query. Is that increase in overall cost, going to be offset an increase in revenue driven by semantic searches?

SIGNUP NOW, join a free plan or a free trial to know whats best for you. 

Posted in eCommerce Site Search

Extracting insights from search data in your eCommerce store

Posted on December 22, 2016 by


We recently shared a detailed post on the need for Search in eCommerce where we refer to the Search function as speaking to a sales person in a brick & mortar store. So lets continue with the same analogy here.

As a retail store owner, your in-store sales person (search), is interacting with visitors and getting to know their interest in products, colors, fabrics, specifications etc., every minute detail of interest is explicitly shared by your visitors during the search process. This is further fine tuned by the selection of filters to drill down and find that product that will convert them to a customer. This treasure trove of data (search queries & filters) should be used by your marketing and planning teams to improve the topline and bottom line of your business.

Topline impact

With access to search data and resulting visitor engagement details for these queries – impressions delivered, what was clicked, position of clicks, time spent, visitor segments etc., your team has data to understand what your customers seek. 19660747568_02f3186094_b

For example, if the top search query in New York City, is for “Kohler Faucets” and in San Diego is for a “Moen”, for the same data period across segments, it would be wise to promote products that match that query or specific products within that query in your SEO and SEM campaigns, geofenced to New York city and San Diego. This process of creating focussed marketing campaigns to target each customer segment is bound to deliver higher ROI for your digital marketing budgets. The only caveat is that you need “enough” data to make sense out of it.

Search data can also be used to decide what banners within the website, to guide visitors to a landing page with relevant results. Our advise on home page banner strategy is to dedicate 2/5 banners to Search data (historical data) and 3/5 banners to external trend data. Hence if your top site wide searches are “Faucets” and ” Moen”, create a landing page dedicated to these two keywords, that include products which received the most engagement for these keyword searches and maybe throw in an offer or incentive, to accelerate engagement, conversion and revenue generation.

Bottom Line Impact

Analyzing search queries gives you access to customer demand data. This can be used to better plan stock to ensure supply meets demand. For example, if your customers are seeking “Ruby rings” and only 5% of your stock in rings contain the Ruby stone and over 50% is Diamond rings, there is a good chance, you are going to be subject to low inventory turns. This is not good for your cash flow and will drive the “Discounting” act if you need to move the stock. Stocking products that are in demand could increase the probability that customers are less inclined to discounts as they need it NOW.

SIGNUP NOW, join a free plan or a free trial to know whats best for you. 

 

Posted in eCommerce Site Search

How Amazon Site Search algorithms affected Flintobox in SEM

Posted on December 21, 2016 by


Want Amazon like Search experience in your online store?  Signup now and see your visitor engagement improve or read from one of our data analysts on the inside workings of Amazon Search.

Recently a fellow entrepreneur raised an issue on unfair acts by Amazon.in infringing on their trademark name “Flintobox”. The issue came alive because Amazon.in had bid for the keyword “Flintobox” on Google and given that it’s Amazon, there is no way a startup can outbid them. Also, legally no company is allowed to bid on a name that is trademarked by another entity. Below a screenshot of the dispute in question.

amazon-trademark-violation-2016-10-18

This has been rectified by Amazon, but it sure caused some heartburn for the Flintobox founders, a few folks at Amazon and many small businesses that feel threatened by such incidents.

amazon-response

It always confuses me when large, funded players are willing to outbid, underbid or even lose money to acquire your customer. This probably led to the founder sharing his woes across the social media where it was retweeted, shared and hence reached my timeline. My friends at Amazon, who speak highly of the company, insist that something like this must have been a mistake and not some personal agenda of any category manager to acquire customers by breaking the law. So, I personally spent some time trying to understand what could have happened, given that Amazon has been a very big influence in my life.

At Tagalys, one of the products we sell to our customers is personalized search as a service and we think the internal Amazon search tool, something that most visitors engage with, might be the cause to the above dispute. Here is our take on what could happened. We hope to hear your feedback as it will also help us improve what we live to build everyday.

Today (Dec 21st, 2016, 1358 hours) if you visit amazon.in and search for “Flintobox” you will still find search suggestions, even though Amazon.in does not carry any stock of the Flintobox products.

flintobox-search-amazon

Now everyone knows “Search” at Amazon is best in class, hence there is no way Amazon will show you Flintobox in search suggestions, if the engine knows products are – OUT OF STOCK. But if you click on any of the suggestions, it leads to a Search results page, that as expected, does not display any Flintobox products instead it lists Einstein box or Xplora box.

explorabox-jpg einsteinbox-results

This leads to two possible reasons, when sellers upload products onto Amazon.in, they upload details about the products including tags, search keywords, potentially even synonyms. We assume, that these products had the “Flintobox” keyword somewhere in the seller upload sheet.

Another reason, though highly unlikely, is that Amazon dynamically detects that products sold by FlintoBox, Einstein box, Xplora box are targeting the same customer segment. Hence even before a customer visits a “No results” page as Flintobox is not in stock, it redirects them to a page with products that will appeal to the same customer segment. Thereby ensuring engagement and potentially conversion.

But what does all this have to do with an ad created for “Flintobox” by Amazon on Google?

Every eCommerce Search or Site Search engine worth its salt, collects, groups and analyzes “Search” data and how visitors engage with the results across segments. Search is demand data directly from customers and visitors telling you what they want. There is also a high probability if X volume of visitors ask for something within your store, there are many more out there (Search engines like Google) who may want the same.

“Flintobox” as a keyword led to Search results and had engagement. It still continues to do so. For the category/subcategory, their search volume must have met certain minimum criteria and also led to engagement – views, add to carts, buys etc.,. We assume, Amazon has an inbuilt or uses a 3rd party keyword bidding tool for Search engines like Google etc.,, that studies keyword data, with engagement and dynamically creates a landing page (at a category or subcategory level) provided the real time bid requested by Google falls within the budget of Amazon. And since the dynamic page created for the advertisement is powered by Search keyword data, the keyword bidding tool has an active keyword, products to display and bid within budget and voila the landing page is created (This is a screenshot of the landing page reproduced from the blog posted by the Flintobox founder, hence products displayed may not not current)

flintobox_search_listing_on_amazon1

So what could have been done to have avoided this incident?

If the above assumptions are correct, then the Amazon seller services team should have more checks in place when sellers upload data. Google today will not allow you to bid for a search keyword that is trademarked by another entity and something similar within Amazon Seller services could have voided this incident from happening. Another way, although rudimentary is the compare the seller upload tags/keywords data with the Brand names stored within the Amazon database. This may not cover trademark infringements, but will definitely avoid Brand X showing in suggestions of results when Brand Y is what a visitor is searching for.

I feel this was not done on purpose, but sometimes a small mistake by a large company is enough to make a big impact in the ecosystem around them. While an apology may have been issued, it does not help with the loss in cash flow that many of the smaller companies rely to grow. Fortunately Flintobox survived to tell a story, many others may not.

SIGNUP NOW, join a free plan or a free trial to know whats best for you. 

Posted in eCommerce Site Search

The need for personalized search in your eCommerce business

Posted on December 20, 2016 by


eCommerce Search, Site Search or Product Search are a few of the terms customers refer to the experience of allowing a visitor quickly find a set of products that match a search query entered in the search bar within an eCommerce store. Search is key revenue driver at the lowest operational cost for leading retailers across the world. Data recorded by Tagalys across clients shows that although less than 10% of visitors search, they drive anywhere between 30% to 40% of the stores revenue. This is evident as leading global retailers display a prominent search bar with a clear call to action, that drives visitors to search for products. Interested – Sign up now.

amazon search bar

walmart search bar

Site Search is a product discovery channel that can deliver conversion rates almost 2X higher than regular listing pages. These numbers hold water only if you have the right engine and not based purely only on keyword relevance (Search 1.0). Some of the other benefits of Site Search are reduced time to checkout, higher product views per visit and increased order value per customer. But there are many instances of online retailers giving little or no importance to the Search experience within their store. If you already know this, Sign up now and improve your visitor engagement.

Lets take a step back and consider offline retail, cause online commerce is only an extension of offline retail. Hypothetically, you own this fabulous brand and open two stores in the same city. They have the same inventory (Product catalog), physical store format (UI) and display Merchandising (UX). But one has a shopping assistant and the other does not. The store with an assistant will deliver more sales and the amount by which the sales will improve will depend on the aptitude of the shopping assistant. Most visitors with an intent of purchase will interact with the sales person – “Do you have shoes?”, that leads to relevant questions “What brand, size, color?”, resulting in products that best suit the query. This is what Search 1.0 for eCommerce is expected to do. Understand what your visitors seek (Search query), ask relevant questions about that query (Filters) and show products (Search results) that match the query (No usage of data analytics). Then came along a smarter shopping assistant (Search 2.0) who started to consider what was sold, what products were viewed and visited the dressing room. With this intelligence, products shown not only match the query but also consider store analytics to support the increase in sale probability. But today, a sales person remembers you, knows what you like or what someone with your shopping persona may like, will show you products for the same query based on individual persona data. Ensuring products shown are not pushed based on store data, but personally relevant to you as it is based in individual shopping persona data. This is Search 3.0. Interested – Sign up now.

shopping assistant in store

The rise of Search 3.0 or personalized search is driven by the “Attention Economy” and the rise in mobile first discovery. Almost 60% of visitors engage with an eCommerce store via a mobile device, they are on the move, pressed to time and prone to distractions. Personalization of Search improves visitor engagement as it makes Search a personally relevant experience.

So if you think intelligent or personalized search will boost sales for your eCommerce business, start considering the following

  1. Make vs. Buy
    • What will be lost revenue over 8 to 10 months by not installing intelligent or personalized search
    • What will be increase in operating cost when internal resources are deployed to build the same inhouse?
    • What will be monthly recurring cost (hardware, software and human resources) to build, maintain and continue keeping abreast of the best in technology?
    • What should I budget every month to gain access to reliable intelligent or personalized search almost instantly?
    • What uplift in sales will a 3rd party Search solution offer my eCommerce business
  2. What will be increase in visitors who search, if I make the search bar more prominent with a clear call to action and resulting increase in revenue if my search conversion were to improve by a minimum of 50%?
  3. What will be the increase in cash flow if visitors become customers faster?

SIGNUP NOW, join a free plan or a free trial to know whats best for you. 

Posted in eCommerce Site Search