Tag: SEO

Simple E-commerce Enhancements for Better Search Click-Through Rate and Conversions

Posted on July 11, 2019 by

Instant access, 24/7 accessibility, and quick turnaround – these are the three main requisites of the E-commerce world. Consumers are craving constant improvements in their shopping experience. If you don’t have it, it’s easy to jump to a competitor. They don’t even need to search for one, Google provides all the answers. 

So in such a competitive world, how do you keep up? How does your business survive?

You might’ve created an awesome website, listed great products – you’re doing everything right, but you’re just not getting enough visitors. Fewer visitors means a lesser number of purchases.

But nevertheless, many E-commerce retailers do so well, so there must be something they’re doing right. The best way to find this out is data! 

Data from past experiences will show you that there are plenty of ways to not just survive but thrive. You just need to know the tricks of the trade. Here, we focus on increasing organic click-through rate (CTR) as it plays a pivotal role in increasing conversions, and ultimately, increasing revenue. 

What you need to know about click-through rate?

Click-through-rates are simply the number of times people click on your website’s link compared to the number of times it appeared in search results or in advertising impressions. Though you may appear in SERPs (Search Engine Page Results), you still need to entice the consumer into clicking on the link to visit your page. 

Even if you’re ranking high on Google’s search results, it’s no good if you have a low CTR. But when you look at it the other way around, a greater CTR leads to a higher quality or relevance score. This helps increase your SEO ranking and save on cost-per-click rates. 

So now that we know a little more about CTRs, let’s get to making it work to your advantage. We’ve got a few simple enhancements you could incorporate to increase your click-through rate.

1. Improve your titles

Seems like such a simple uninteresting ‘been there done that’ idea but titles have a huge impact on readers! Whether or not the user clicks on the link largely depends on what they see first. Unfortunately, now many of the titles are just rehashed SEO optimized titles with a keyword stuffed in. These boring titles won’t get you far. 

How do you write a click-worthy title and still optimize it? It’s a tough job but it isn’t complicated. Using statistics, pulling on emotional strings, and striking home works way better than generic titles. 

So find out what your user really wants, or what problems they truly are facing, and design your title around that. 

For example, 

“10 things you need to know about click-through rate” 

wouldn’t work as well as 

“How to increase your click-through rate by 20%”.

In the second title, you’ve recognized the fact that the user is looking for ways to increase CTR rather than just telling them 10 things about CTR. You’ve also added “20%” giving them an estimate of how much they can drive up their CTR. This also solidifies the fact that you are basing your article on data and facts.

2. Make your URLs descriptive

Always ensure your URLs are SEO friendly, but you also need to ensure their readability. Ugly URLs don’t do well when it comes to click-through rates. We recommend using a URL that’s easy to read by the user and search engines! Simply match your URL to the title and remove any unnecessary words and keep it short.

For example: 

www.abc.com/blog/CTR/ten-tips-on-how-to-improve-click-through-rate/2345/#quick-066

can be optimized to 

www.abc.com/blog/ten-tips-improve-click-through-rate. 

Other than hyphens that are used to break up the words, all other punctuation can also be considered unnecessary characters and can be left out. 

Keep your URLs relevant, clean, short and easy to read to ensure your users know what the page is about. 

3. Meta descriptions

Meta descriptions are the snippets that appear under the title in SERPs. You need to give the reader everything important they need to know about what they just searched for. Highlight the best parts of your content or your product. 

You need to fix meta descriptions that are too short, too long or if there are duplicates. There are tools that can help you keep track of the length of your title. If you have a WordPress site, you could use the Yoast SEO plugin to make your meta descriptions perfect. Apart from meta descriptions, Yoast SEO plugin also suggests other optimizations to gives your site or content a boost to rank higher on Google using an SEO best practices checklist. 

But at the end of the day, remember to give the reader just enough of the answer they’re looking for. If you give it all away, they might get the answer to what they’re looking for in the meta description and never need to click on your link. A well-crafted meta description can improve your CTR.

4. Using rich snippets 

Google’s rich snippets enable web marketers to display their reviews and ratings that will give the customer a good sense of what others think of their business. These snippets help draw the user’s eye to the result and give them a clear idea of what they can expect from the site. This makes a great difference to CTR. 

Following CTR through by optimizing your conversion rate 

Now that the customer clicked on the link, the job is definitely not over. It continues on into getting the customer to make a purchase. A high CTR doesn’t always correlate to a high conversion rate. 

When a person lands on your eCommerce store, if relevant products aren’t displayed, if your page isn’t categorized well – basically they don’t see what they want – then you’d only see an increase in bounce rate and not in your conversion rate. Remember, if you presented a title and description in the search results that didn’t match the contents of the page, your potential customers are sure to leave without a second thought.

You might realize that when a customer comes to your site, they might be seeing the latest products you updated, rather than seeing what’s the best or most relevant products. For example, you know a particular dress sells really well, but when a customer looks for dresses, your bestseller isn’t showing up in the top results.

74% of online shoppers say product selection is important during the online search process.

In order to cater to this statistic, you can narrow your target audience by categorizing your pages. So instead of a page displaying a wide variety of products, every page can carry specific products that are closely related or would be liked by a particular kind of customer. 

Apart from this, descriptions and titles for every page and product can greatly influence the customer’s choice. 88% of shoppers felt product details were extremely important to their purchase decision. 

So once the customer is in, you need to ensure these things are in place:

  • Display relevant products. If a user searched for a mahogany dining table, the products displayed should fall under that category. Displaying items that closely match the search would be acceptable. For instance, since mahogany is on the darker side and is more expensive, your search results can display other items that fall under a similar color, quality, and price range. 
  • Give them all the details of the product that would help them figure out the right one for them. Taking the same dining table search, it would be helpful to the customer to know the exact dimensions, color, weight, the primary material used, and how many people it can seat. 
  • Use great high-quality images from all angles. Since the visitor can’t walk around the store and see it in person, nor can they try it out, the alternative would be to give them a good view of the product. A great tactic used here is to measure it against an average human silhouette. This gives the visitor a good sense of how large the product is. You can also include a zoomed in photo to see the material up close. This can also inculcate the fact that you have confidence in your products!
  • You could also give the user the option to do a site search for specific queries they might have. This helps potential customers to narrow down the products displayed to only the ones they want to see.

To get complete control of your visitor’s experience, right from clicks to conversions, you could use eCommerce solutions like Tagalys that help sort your products and curate category & collection pages. Tagalys helps improve conversion rates by enhancing user experience. Through meticulous curation in site search and category pages of online stores, it displays relevant products that capture the customer’s attention and are most likely to convert to a purchase.

So, there you have it. Simple ways in which you can increase your click-through rate and follow up with getting them to purchase your products. eCommerce may be a tough game to play in a market so wide, but if you have the right tools and tricks of the trade, you’re bound to be a cut above the rest!

Posted in e-Commerce General
Tagged in

Three reasons why Tagalys powered product listing pages are likely to rank higher in organic search results for Magento and Shopify

Posted on July 5, 2019 by

The challenges in eCommerce are increasing every day and SEO is an important challenge faced by all. Search engine optimization (SEO) is the process of increasing the quality and quantity of website traffic, by increasing the visibility of a website or a web page to users of a web search engine. 

Retailers invest in a  lot of effort and money to improvise the user experience & interface of their online store but fail in bringing high volumes of recurring organic traffic to their store. This part is very important for retailers as it directly impacts customer acquisition costs and the profits at the online store. Product Listing Pages are usually used as a source of generating high volumes of recurring organic traffic to the online store. These pages are most relevant for online shoppers as it immediately gives them a choice of products to engage and find something of interest. Creating and maintaining product listing pages in Magento or Shopify stores is a tedious task as it requires a lot of manual effort.

 

(Creating a custom sale page in 30 seconds using Tagalys)

 

Using Tagalys retailers can create product listing pages in seconds & its visual merchandising capabilities completely enhances the experience delivered to the visitors. The Tagalys powered pages are dynamic and automated. These pages are also Search Engine Optimized if the meta-variables like title, description, meta keywords are set during page creation. 

Assuming SEO variables are set during page creation, some of the reasons why Tagalys powered pages are likely to rank higher in organic search results are as follows

Dynamic product sorting 

Products in Tagalys powered pages are by default sorted by the trending score. This score assigned to each product is dynamic and is based on the overall performance of the product and its tags across the last 30 days. As over 70% of visitors click on products on page 1, T-Score sorting increases the CTR (Click-Through-Rate) of the page as trending products are displayed on page 1. This increase in CTR & reduction in page bounce rate, improves the page ranking in web search engines.

Quicker API response time 

Faster load time with the trending products is more likely to keep your visitors engaged. Almost 60% of online visitors engage with online stores using mobile devices and mobile devices are notorious for high latency. Pages that load very slowly (after applying filters, sort options, etc.,) will cause visitors to leave the site almost immediately.  Tagalys powered pages respond in less than 90 milliseconds making the page load duration fast, bounce low & CTR high. This increase in CTR & reduction in page bounce rate, improve the page ranking in web search engines.

Dynamic page variables 

Tagalys allows retailers to add dynamic page variables using smart keys. A Smart Key is a dynamic variable that changes automatically based on changes made to the product table at your online store E.g., Product count, sale price, product tags, etc. It keeps the meta content refreshed always and gives visitors detailed information on the page. Dynamic content also keeps your content relevant & fresh.

 

(The above page variable is added using Tagalys Smart Key that varies automatically based on the store data)

 

While the above reasons help improve the performance of a page that contributes to page ranking, page ranking improves at a faster pace when high performing pages are subject to high traffic. Hence online retailers should ensure other onsite & offsite optimizations like interlinking, alt tags, mobile speeds etc., are in check to ensure the raking increases as expected.

Tagalys powered pages have a high CTR & lower bounce than pages created on Magento & Shopify. Assuming onsite & offsite optimizations are done, you can be assured to have high page ranking on SERP (Search Engine Results Page). Tagalys also saves a lot of time and resources spent on SEO. 

Tagalys maximizes conversion rate & gives merchants visual control of products displayed in Site Search & Category pages at their online store. To know more about our solutions and features, get in touch with us now.

Posted in e-Commerce Product Listing pages
Tagged in

How does Amazon get its Organic Traffic

Posted on March 22, 2019 by

Think of the last time you walked into a retail store, how exactly did you make your purchase? Let’s say you walk in with the intention of buying red shoes. All you would have done is look for signages to, or ask someone for, the section which has red shoes, take your pick, and then buy it. But, let’s say that you walk into the store but there isn’t anyone to point you in the right direction, nor are there signs which take you there. You may either get overwhelmed and leave the store right away, or you may spend an abnormally large amount of time looking for the product and buying it but coming out of the store with an extremely bad experience.

Organic Traffic in Amazon

Now, let’s compare this with the online shopping scenario. A first-time shopper is more than likely to search for a product on Google first, than going directly to an eCommerce website. Here, the google search is analogous to signage or store assistant in an actual retail store. So, if someone types the same red shoes on Google search, the first search result (apart from the Ads) will often be an Amazon listing page, which leads users to a page that has only red shoes, hence shortening the time to purchase. Let’s think of some other google searches that online shoppers might do

Light blue formal shirts
Buy JBL headphones
Black watches for kids
Powerbank for iPhone

Amazon will be among the top 3 search results for any such search results relevant to online shoppers.

Amazon has monthly traffic via an organic search of approximately 650 million. Regardless of the industry that an online retail store might be in, it is extremely challenging to compete against the might of Amazon. So, how does Amazon manage to rank itself on the top of Google search for almost every search query by online shoppers?

It’s the sheer amount of category or listing pages within Amazon

Yes, Amazon has category pages for any and every kind of long-tail keywords on Google search. Whether it be Shoes, Nike shoes, Nike running shoes, men’s Nike running shoes, or any keyword in similar terrain, amazon will have unique, search optimized listing pages for each of them. These listing pages are also dynamic, and content is constantly refreshed to keep the pages optimized for search.

So, how does Amazon create these many category pages for its website? And how does it identify what are the category pages that need to be created? The easy answer is it lets its vast amounts of data and AI does the dirty work and automates the creation of listing pages. However, on digging deep, there are a few signals that they might be used to identify the category pages that need to be created

  • Search patterns on Google that bring in search traffic into the Amazon website
  • Search queries on Amazon’s internal site search
  • User behavior in terms of the filters they use in their category pages
  • Cart abandonment data to understand the product, brand, and/or price preferences of visitors

Theoretically, this would seem like a straightforward task of identifying gaps between search queries & existing pages and then creating category pages for those. However, manually creating a category page on Magento or any other eCommerce platforms is a painstaking process, with each page taking a minimum of 30 – 60 minutes. Does automating the category page creation and generating hundreds of such pages, the Amazon way, within seconds sound exciting? Talk to us today to learn more.

Posted in e-Commerce General e-Commerce Product Listing pages e-Commerce Product Recommendations
Tagged in

SEO tips for Magento Commerce – Interview with Candere.com

Posted on February 15, 2019 by

Akshay Matkar is the Head of Digital Marketing at Candere.com, one of the leading online jewelry retailers in India & also part of the $1.5B Kalyan Jewelers group.

Candere is built on Magento Commerce, primarily because of the flexibility it offers in connecting the back end processes. Unlike Shopify, BigCommerce or other platforms, Magento was selected because it supports the complex supply chain or the back end of Candere, which cannot be supported by other platforms. Magento does not offer any advantages from an SEO function, hence Candere completely relies on the expertise of their SEO team and 3rd party tools, to drive organic traffic to their online store.

Akshay & team rely on the Google Search console as the Holy Grail of understanding the results of their SEO efforts. An interesting note is that the team is not only interested in the organic traffic to their store, but also the market share of the search keywords where candere.com is visible. Market share was an interesting metric because it is a trailing metric. This means that the higher the market share of keywords for which you are visible today, the higher the increase in organic traffic into your site tomorrow. This is Brand visibility & they want to be seen for anything relevant to their market. Visitors may not click on the page URL in search results but have registered the brand name, which also improves brand recall. In less than 3 years, Candere.com has increased the market share visibility from less than 5% to over 15%, that’s a whopping 300% increase in brand visibility, with the efforts of this team, led by Akshay. In the battle for eCommerce, Google continues to be the biggest winner. Online jewelers have to pay between $0.5 to $2 per click to bring a unique visitor to their store. With that in mind, Akshay & his team have been a significant impact to the bottom line of Candere, by scaling organic traffic. While this did not happen immediately, their efforts for the past 2 years, have exceeded in returns if you were to look at how much they would need to spend on Google to bring in this traffic via Ad Words.

While Candere has made significant expansion in their organic traffic, Akshay is modest to agree that he looks up to his competition as they are still the leaders in organic traffic for the vertical. He especially compliments them on their URL structure, interlinking of pages & site performance that have all contributed towards better SEO ranking of the domain and the pages.

SEO Requirements:

Akshay and team follow multiple strategies to improve organic traffic. A few keys areas are mentioned below

Fresh Content: The team continues to monitor the performance of all the listing pages and when they detect a downward trend, the team adds/edits content blocks on the pages to ensure the content is relevant to the relevancy of search queries.

Product Assortment: One of the challenges on platforms like Magento, is that the product sorting is static or sorted using a simple field like new, most sold, most viewed, etc., Due to the nature of how visitors engage at on online store, the simple logic does not work across most pages. The lack of intelligent product sorting changes also leads crawlers to believe that there has been no change on the page. Akshay & team are in the midst of integrating technology that can help them automate this process at scale to contribute to page refresh & SEO ranking

Internal Linking: Akshay goes on record to say that if there are 100 parameters for SEO, internal linking is in the top 3. He feels this builds a hierarchy of the online store, to help a search engine better understand the structure of listing pages within an online store. For example, if an online store has over 1000 pages but each page is not linked to each other, this reduces the SEO juice that flows from the domain to the individual pages. While the IP behind how SEO scores are calculated will never be revealed, what Akshay says makes perfect sense. From an SEO standpoint, you can not treat each page with the same importance. Pages linked from the top navigation or another listing page should technically have more SEO juice that an individual page located only on the site map. Hence a page that is linked more across the online store will attract more traffic, which contributes to the SEO score and that can attract organic traffic with better SERP rankings. Akshay added a word of caution that merchants need to balance the need for SEO vs. the expectations of the online visitor. He means while internal linking is more an SEO activity, it might confuse the visitor at your online store who could either be in the awareness, consideration or buying stage, by randomly clicking and being distracted in their journey.

Page Format: Merchants invest in SEO efforts across the home page, landing page, product listing pages and sometimes even product pages. From the breadth of experiments conducted by Akshay, he confirms that the product listing pages & the home page are what they invest their time for SEO optimization. Landing pages are not a great idea for SEO optimization but mainly used for other campaigns. Akshay did not spend time talking about product pages for SEO, but I am certain they follow the basics to check the boxes. Product pages are not a great source of organic traffic that converts.

SEO Content: If you have the right interlinking, page format, URL structure & product sorting, you would still NOT get a single organic visitor without the right meta content on the page. Adding content is time-consuming because if you add too much content and “Stuff” keywords, you might get initial visibility but as your bounce rates increase, your page ranking will decrease. Hence it is important to create unique listing pages with unique content. When Akshay originally mentioned about increasing their market share 3X, it has to also do with the time invested in creating unique pages to attract 3X more traffic across thousands of new search queries that address the exact segment served by Candere. While some merchants may not consider the products as content on the page, Akshay feels that there needs to be minimum content or 16 products on a page, before they invest time to optimize it for SEO. If you are not familiar with “thin content” here is a beginners guide to thin content

HTTP status codes: 301, 302, 202, etc., These signals are used by Search engines to ensure the crawler is efficient. It would be impossible for any search engine to crawl the internet without checks & balances in place. HTTP status codes are a very important part of making sure the crawlers are efficient in the requirement to gather data from the internet. The team at Candere fanatically ensures HTTP status codes are in place. They have internally built tools to manage 301 redirects because for an SEO team, URL changes are constant and they required an efficient way to manage them.

Google analytics: The team at Candere looks at GA as a source of data for Google, before considering it as a reporting tool. This belief pushed the team to invest time in the early part of 2017, making changes to ensure the data was captured correctly in their GA. This also led to the 3X increase in market share and a correlated increase in traffic. If you have incorrectly configured your GA, tracking partial or inaccurate metrics, Google would get that as input data in and consider those data points in their SEO scores for your domain & individual pages.

Tools for SEO:

Search engine optimization is part science, part math. While you can try & improve the ranking of existing pages, what about the pages that you are not ranked but your competitor is? Candere uses tools like SEO Profiler & Ahrefs to benchmark competitors and close the gaps. Ahrefs is used mainly for link analysis, which Akshay passionately shared earlier in the section of SEO requirements. SEO Profiler is used to continuously analyze the market, competition & Candere, to find errors, opportunities & gaps, in their existing SEO strategy.

He cautions to say that these tools are no silver bullets in SEO. Merchants should start with the basic package form such tools to check the basic SEO requirements in place first – URL structures, Page formats, HTTP Status codes, GA implementation & Content strategy. Once this is in place and the store is seeing a growth in traffic & engagement (low bounce, higher CTRs), only then should they invest in complete packages from these tools to put fuel into their SEO rocketship.

We close the conversation talking about AMP sites. While Akshay has observed a push from Google to migrate towards AMP sites, he has recognized that none of the major online retailers use AMP. While AMP makes your mobile store significantly faster in load times, it is done at the expense of removing all external plugins like chat, search, recommendations, popups et., that help drive user experience. While AMP may be helpful to online stores that are custom built and have everything else built in-house, it will hamper the conversion rate of the merchant using platforms like Magento, Shopify, etc., that rely on 3rd party tools to improve their online shopping experience. While Akshay does not reveal specifics, he says they are investing to improve the mobile shopping experience of their visitors as that is where over 80% are today

SEO Strategy:

Using the above-mentioned tools, the team has created a master keyword list and have marked the search keywords wrt search volume, competition. The simple 2 X 2 matrix, helped them identify the low hanging fruit which they went after and acquired. As the market has matured, where most high volume, high competition keywords are addressed, they are moving across the matrix to address medium volume (short tail) & low volume (long-tail) keywords. His experience long tail allows him to confidently say that the conversion rate for long-tail keywords is 2X more than short-tail keywords.

We closed the conversation, with Akshay sharing SEO conspiracy theories that involved some known entities. Ironically, I have felt the same & also heard the same from a few other merchants. More on that another day, when we both are no longer in our current roles, but for now. Its thank you.

About Tagalys: Tagalys helps SMB Mid Market online retailers using Magento & Shopify with high conversion category/product listing pages & Site Search.

About Candere: Candere by Kalyan Jewellers, is an initiative to make fine jewelry more affordable and accessible to you than it ever was. Candere’s philosophy is to offer customers extraordinary value on the largest inventory of fine jewelry and certified diamonds with the comfort, convenience, and security of online shopping. It’s a world-class shopping experience from the convenience of your own home.

Posted in e-Commerce General e-Commerce Product Listing pages
Tagged in

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 engine 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.

Tagalys maximizes conversion rate & gives merchants visual control of products displayed in Site Search & Category pages at their online store. To know more about our solutions and features, get in touch with us now.

You can also read more at Intelligent Product Listing pages here.

Posted in e-Commerce Product Listing pages
Tagged in

Image Search vs. Text Search in eCommerce

Posted on December 26, 2016 by

At Tagalys, we extract text data from the product catalog to start data enrichment, hence we are biased towards text-based tagging 🙂 But let us also share some of the advantages and disadvantages of the same so you can evaluate for yourself.

VERTICAL AGNOSTIC:

Tagalys can start working with an eCommerce company across any vertical and start showing improvements from day one. That is why we never hesitated to take on clients that sell apparel, shoes, accessories, jewelry, food and building material as long as they meet certain minimum requirements of scale. This is because, our engine relies on text data that is usually available in various parts of the product catalog and unlike image recognition we do not need any training data (vast sums), to reach a 90% accuracy in auto-generating tags.

DATA AVAILABILITY:

Image recognition products that are vertical focused extract tags from the image. The advantages are that if the engine is trained properly, it has the ability to extract fine detail tags at scale with over a 90% accuracy. Hence an image of a dress can lead to the extraction of externally visible tags tied to color, length, sleeve, neck, design, etc., Text tagging engines like Tagalys rely on the content, hence if such details are missing they will not be considered in the analytics of visitor-product engagement. But this also means if Tagalys cannot find such tags, nor can your online visitors or search engines like Google that rely on text data to understand the product better. Hence it is in every retailer’s best interest to ensure all details about the product are clearly outlined in the product catalog to promote improved product discovery both on the website and also in search engines.

The second question is how much of an added benefit will the retailer have in terms of engagement/conversion/revenues by auto extracting tags from images? As mentioned below, costs for such a high accuracy image extraction engine are higher than text tagging, leading to higher prices for the customer.

COSTS:

As text-based tagging does not require vast sums of training data to get started, but on available data, our cost is much lower than image recognition companies.  The costs for an image recognition company are not only acquiring vast volumes of images to build a database but also the time it takes them to create this database as that impacts the NPV of cash on hand. As our costs are lower, these savings are passed on to you, the customer.

CORE COMPETENCY:

If a retailer’s problem statement is to improve personalization or showing the right products/content to the right visitors, then you need a personalization engine like Tagalys, whose focus is to create data models that simulate the shopping persona of visitors. But if your problem statement is to auto-extract tags from images as there is no content, then a visual recognition engine is what you need, provided it has been previously trained with millions of images in the same vertical.

APPLICATIONS:

A personalization engine like Tagalys can be applied to any channel where a visitor is likely to discover products. This could be a listing page, search results or recommendations widgets.

Visual or image recognition engines, whose core competency is to identify the image and the metadata (tags) from the image is best applied in the Similar products recommendation widget. That being said, we recently worked with a jewelry retailer who switched from an Image Recognition to Tagalys recommendations and realized cost savings in monthly fees and higher revenues driven by better conversion from our recommendation engine.

Image recognition is also confined to verticals where there is enough data to improve the auto tag accuracy levels. If they need to be applied to any other features of eCommerce, then a personalization engine has to be built on top of the existing visual/image recognition engine.

ERROR TOLERANCE:

A combination of image recognition to extract the tags and human tagging might help reduce error tolerance. Product catalog data that is a must-have for an e-commerce platform and is usually entered by humans. This task sometimes has errors or incomplete submissions, that can impact the pattern recognition algorithms in Tagalys. In over 90% of the cases, we find the data to be complete with some minute details missing by the data entry operator, but very seldom incorrect. This is also because incorrect data can negatively impact SERP score, as the content displayed on any listing page is based on the text data behind the product. Hence while we have seen good data from the catalog itself, adding an image-based system to identify tags in verticals like fashion, can extract additional data that can be leveraged by Tagalys.

Tagalys maximizes conversion rate & gives merchants visual control of products displayed in Site Search & Category pages at their Magento or Shopify online store. To know more about our solutions and features, get in touch with us now.

Posted in e-Commerce General eCommerce Site Search
Tagged in

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 of the above dispute. Here is our take on what could happen. We hope to hear your feedback as it will also help us improve what we live to build every day.

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 asks 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 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 on 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 on 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 what’s best for you. 

Posted in eCommerce Site Search
Tagged in