We're discussing personalization for e-commerce and Retail with Sean Milani, the chief technology officer of algo Lea. We power it search and browse and recommendation experiences across 17 thousand websites all over the internet. Where actually the second biggest search engine in the world behind Google, we power over 1.75 trillion requests every single year. So a very exciting powering a lot of the fun. Datian the internet. I have to say that at cxo, talk. We're actually one of your
customers we use. I'll go Leah, on cxo talk.com. It's great to talk to one of our customers, and it's great to hear that. We can help our your experience as well. You're focused on e-commerce and Retail. So why don't you give us just
the high-level overview of that? We actually serve customers across a whole range of Industries, but e-commerce is obviously the one of the ones that were best known for the reason is because search is so important as part of Whole Discovery journey in e-commerce, people love e-commerce stores. And one of the reasons is because they get such an incredibly wide selection of products that they can shop for. But it's also hugely overwhelming for a shopper.
It would be like walking into a physical store and it's the size of like, a huge Stadium. You would just have million items to choose from but it's it's very overwhelming. They call this the Paradox of choice and more choice. You provide a customer often the less satisfied they are or the more overwhelmed They are and their experience can actually deteriorate with more choices. E-commerce brings a huge
opportunity. But it's also means that we have to have new tools and Technologies to be able to help customers and guide them through this experience, showing how do advancements in Ai and machine learning such as chat GPT effect, this search landscape as you've been describing he hopes that around 20-30 years now but the experience to a shopper still feels very much. Like it could come out of the
1990s during the.com. If a lot of e-commerce, sites are really just a product database or a product catalog that have a user experience on it. You still have to talk to the website and the way you would talk to a computer, right? You have to type in like specific words, you have to click on different filters to kind of narrow down the selection and this is going to
change dramatically now. So a lot of these language models that are powering chat GPT of exploded in size and sophistication over the last few years and there. Now able to actually really understand humans in a way in which humans can use not natural language and understands the intent and the concepts behind what they're looking for.
Sean can you elaborate on? How may I help some make this shopping experience, better for the user, you don't need to be able to talk to the computer anymore. The computer can actually understand you. So what we're seeing is people are using far more expressive language. Now, the number of words that they're typing into the search box, Is becoming significantly
larger. It's like doubled in size in the last couple of years, but also people are expecting experiences that are far more sophisticated, and personalized. As I enter in searches or I click on filters or a view products, it expects the experience to adapt to me to really understand what I'm looking for to remember me, when I turn up to the site, Shawn you've described how natural language search just makes it easier for end users. Your Chief technology officer of algo.
Leah, can you give us a glimpse behind the scenes of how this is possible? There's been a real Quantum Leap and what we're able to do over the last year or two, as Chachi beauty is really demonstrated to the world that you can interface with users using natural language. Both as the inputs to ask questions but also as an output to be able to answer their questions.
But we're fundamentally changing the way in which we search and retrieve information with these Large language models in these new breakthroughs. So, instead of using the actual word, we're now actually taking words and we're turning them into something called a vector. And the vector captures, the concept, and the Nuance behind, either the word or the phrase of the sentence or your question. That means that we can then go and search through all the products are all the web pages
for other vectors. We turn everything in the index into a vector and then it becomes this kind of exercise where we try to find similar vectors. Just like you use words and try to match them with similar words and web pages. But it means that you can do really, really interesting things to give you a really powerful example is if let's say you go to a website and you actually want to shop for a specific brand. So let's say I want to North Face jacket and if the site
doesn't sell that brand, right? It's able to understand the concept behind the brand. So understands North Face sells outdoor jackets and it can Surface other outdoor jackets that are similar to North Face. We can actually find Specifically designed to solve those problems. Even if the words that you're using, when you describe the problem, don't match the words in the product.
How is this different from traditional search, whether on e-commerce sites or just in just broadly, traditional search is literally just taking the literal words that you type in and trying to find products that use those literal words. You know, a good example is if you wanted to search for chocolate milk or milk chocolate, these are two terms of exactly the same words, but very different categories to
search for. And so it can be very, very confusing sometimes for these search engines to be able to disambiguate the actual words. But when we can translate them into very specific Concepts and really understand the intent behind them. Then we're going to get far
better more accurate results. And I have to say, some of our early customers are just seen incredible increases in the amount of conversions, and the amount of things that Shoppers are able to buy because They're able to find it. Sean you mentioned Vector search. It's a topic that has been around for a long time yet. It's not widely discussed. Why is that? And what are you doing with this? We've known that vectors are a better way to represent.
Concepts Than Words, we've known vectors work from a scientific perspective and we can get great results in the lab but it turns out that they're really hard to scale. Like I mentioned we've Got we do about 1.75 trillion, search requests a year, across 17,000, different websites and to be able to, like, apply vectors on. Every single query is really,
really challenging. Vectors are very, very computationally, heavy it. Take up a lot of memory both in the server but also when you're training and storing them and they're actually pretty slow and expensive to roll out. The Breakthrough that we've recently had is we figured out how to compress vectors, so we can actually compress Them into like a 10 times smaller format, keeping the same kind of relevancy and we can do it at extremely high speeds.
We can take every single query across as one point seven five trillion and we can apply Vector search them. This is the big breakthrough. This Hashem technology that we've built means that for the real world production environments. When you need high speed, you need a reasonable cost and you need really big scale. So this is what makes it practical for you to.
Use vectors in this, highly real-time shopping environment, every single query for our customers, we're able to use both factor and keyword in a single kind of API call. And by using both of these strategies, we actually get a lot more information back and we can use the extra information. Like how many keywords don't match but also how did the vectors match to do a much better ranking? And I think that's pretty unique. I no one else in the industry is able to do this at this size.
Scale and speed that we're doing enough, because we're using this kind of technique called hashing. So, the technology is enabling a simpler easier user experience, that's at the same time, more effective.
What we've seen is about 70% of all of the search queries are actually far more complicated one-off type queries, where people are asking for very specific things, they have a question and that kind of 70% of queers are going, very unanswered at the moment because they're very Uncle to answer with just matching words. So this kind of new AI Vector search is really monetizing and helping solve the customers needs in that 70% of a long tail case and it actually translates
into a lot more sales. Sean we're does personalization fit into this landscape creating a loyal customers. One of the most important parts about creating a great business because you pay to acquire a customer the first time and if they either don't convert that first time because they Find something, or they end up, not coming back for a second or third shopping Journey. Then the economics of acquiring, the customer become pretty unattractive.
How do I create an experience for a shopper where I recognize that there are a customer who's been to the store before? How do I make it feel? So that when a customer comes to my store, that they're going to get a superior experience, the second and third time versus going to a competitor store and that's all about personalization.
Once I've seen what a customer prefers Purrs either through the searches that they make, on the website, or the products that they click on the products they buy, or the products that they click on a. Don't buy, you can observe the entire behavior of the customers, they're shopping and you can learn from it, and you can do that in two ways.
The first way is when they actually appear for the first time, you can really hang on every single, click every single word that they type in and category that they look at. And in real time, even for a shopper that you've never Series never been to the store before. You can start to adapt.
This is the called real-time personalization, and it's kind of like a cold start problem because you really don't know anything about the customer, but I can pretty quickly find out if their brands that they are clicking on more or if their price points that they're gravitating towards. And then I can start to show and put more of these types of products around brands or prices or categories in front of them as they click and discover around the site.
The second really important thing is once they've actually Bought from you, the next time they come back, you acknowledge that. They are a customer that you've seen before and you're able to offer them again. Similar personalized experience and we've seen that these types of personalization algorithms and personalized, experiences can drive substantial increases in conversions. On the second and third visit, as well as this kind of real-time when they're shopping the first time.
So I think it's a very important part of the whole customer lifecycle from acquisition first shopping. Third, and creating a long-term loyal customer. So you're talking about two kinds of personalization one. Is the cold start? As you describe when a visitor, First shows up at your site, but then remembering that visitor, when they come back the second time, the third time and creating an even more tailored and personalized customer experience for them. What is this?
Do to the overall customer lifetime value? You A lot of people when they first do their online experience and move online, they start to focus really on that very first experience of my put some advertising out. It cost me X, those Shoppers turned up to the site and they bought why, you know, here's my return on investment.
But as you start to build a more loyal following and you start to become a little bit more sophisticated in the way, you're thinking about your online business, you start to look at the return over a much longer Lifetime with a customer. You take the whole Time value. And then you set that against the acquisition cost and what it means is, if you create loyal customers, you can spend a higher dollar to acquire a
customer. And so this is really like how to create a scalable customer, acquisition business model online is trying to get your cost per customer acquisition and your customer lifetime value. And the ratio of these two numbers, you want to get that very high. So high customer lifetime value low customer acquisition, how is this different from the traditional? Additional concept of customer Journeys and looking at the total lifetime value of a customer. Typically people will look in
session. So the only look at the specific shopping session that the customer is in Manila. Tribute basically all of the value against the acquisition cost for the customer but as you start to create much more a, I powered experiences and personalization, you can start to account for a much larger amount of It's been created when the customer is acquired, over more and more sessions. So, the technology enables this broader Horizon and more accurate understanding of the customer Behavior.
So, that in effect, you can amortize your initial customer acquisition cost over this longer broader time Horizon, a great e-commerce stores one where you spend, you know, potentially even more money acquiring customers because those customers are going to spend over a series of months and years with you and they're going to become loyal and generate long-term profitability on an individual customer
perspective. So think of it like a PL for a specific customer, right where your profits are the long-term value that they're going to generate through loyalty? And the initial outlay the costs are how much you could spend to acquire them you've touched on this. But what is the impact? Act on the customer or the benefit that the customer receives to encourage them to come back and therefore provide that loyalty to the retailer
from a Shoppers perspective. The benefit is really clear, which is that they're able to find like better products and they're able to do it in a much shorter time period. And it's as simple as like when I turn up to the site, do I even feel like this is a shock, that is kind of tailored towards my needs and to my Tastes so for Shoppers, they're able to find
the things they want. But they also have a sense of feeling of being welcomed and a feeling that the place that they're shopping is the type of place that they want to continue doing business with, because it's it reflects their tastes their style, their values. I think the benefit of this type of Lifetime customer value. Analysis is obviously crucial for retailers, but it leads to the next question. In which is how do we implement this.
You need to have a partner who can help guide you through the process, their companies like out go. Lea and other people who have solved these problems and who have really focused on making the integration and the data collection pieces that are needed to power, these AI algorithms, extremely simple with, a few lines of code,
you're able to integrate with. Like I'll go Lea, unlock our search API working with vendors and working with folks who have dedicated Dated large amounts of resources, time and expertise to solving these problems tends to be the first starting point. And often the best solution, the long run. What are some of the best practices for implementing personalization? Across all of the touch points as customers interact with your site?
The more touch points in the more data that you're able to capture about how your users are using a product, the better, all of these algorithms and reading need to be able to understand Views conversions, but also the product data customers are looking at and having something that can indicate which customers which between sessions. So if they can log into your website, that's the best, but if you can add cookies to your website so you can track them
between visits. That's even that's good. As well. What about the buying funnel? We are customers are in their journey in their relationship to you as a retailer. Customers will turn up on the homepage for example and And you'll have very, very little intent about what they want in the shopping Journey that the kind of high level of the funnel where you're not sure what they're looking for. You want to showcase a breath to them of things that they can find on the store.
And if there are returning customer, you want to have a strong personalization bias on this home page, so that they can see things that are at their taste or style or price points. But as they go and they searched and they start giving you more information about their intent. Really want to focus on the relevance, and on the accuracy of the results, you're showing them because they're giving you a very specific request.
And then, once they land on a product detail page, for example, you have an even more specific piece of information they're interested in this product. So again, you want to become even more tightly focused on your recommendations, you maybe might not want to use as much personalization when you're on a product landing page. Because actually the The Shoppers told you specifically something that they're looking for.
And so as a customer goes in through the Journey, you've got to think about how much intent you really have and either dial-up personalization. When you don't have as much intent or dial-up relevance accuracy. When you have high intent Sean what is the role of real-time data in all of this process. You got to think that a large number of customers coming to your website. It may be the first time that you've seen. It's their first experience. You want that first experience
to be great. So as soon as they click on a single item or they type in a search request, you want that data to flow back into your systems and adapt, your algorithms and real-time you have to have systems that are extremely fast at both ingesting and getting the data in but also like retraining and adapting the algorithm.
So I think real-time data is very important for that first experience but also what you sometimes find is customers come back and they shop slightly different way to their taste. So you also want to be able to adapt In real time, even for customers, that you know, a lot about, then you use this data to make the decision around what to show next to that user. And of course, it's happening. Essentially instantaneously from
the user perspective. Instantaneous, we're talking about milliseconds here that matter in the shopping experience. The faster, the experience is, the more likely customers are going to continue. We've seen 100 200 milliseconds worth of delay. Actually reduces the conversion. And customers end up, leaving the website. So speed is really really important in the Commerce world are there.
Common implementation challenges that retailers face when they're trying to implement this kind of personalization. One of the hard things is making sure that you are capturing this type of 121 data around. This is the user that's logged in. This is the cookie ID that they accepted, this is the session ID for the shopping session.
Ian and making that information available across every click every product view in every single time they come to the site so that the algorithms can do their work, the algorithms can only do so much, they need to be able to identify users. So that's that's really one of the bigger areas where Ecommerce companies need to make sure they've implemented Google analytics pretty well or whatever their analytics
packages. What's the solution to this very common problem using off-the-shelf analytics products? But really focusing on doing a comprehensive job and implementing them. Also, making sure that when you choose a vendor that you really take the extra time when you do the integration to send all the events, send all the clicks and conversions with the right
fields and everything. How do you address the ethical or the privacy considerations that people think of, when we talk about this kind of hyper personalization, one of the things that we have to understand first is that a lot of customers Workers and a lot of Shoppers are very happy to make the trade-off of getting a better experience by allowing the merchant or the site that they're shopping on to be able
to collect this type of data. And when you think about it, that way, you want to make a transparent to them what you're doing. And you want to allow them to make that trade-off for customers who don't feel comfortable with that. You want to enable them to have a very clear trade-off as well and provide a great default
experience. I think it's just important about transparency But also telling customers with the value of it is so they know ahead of time when they click the kind of accept cookies button or decide to log in and create an account for example that by doing. So they're really going to get a far better experience throughout the journey Shawn. Let's talk about measurement and kpis what are the best mechanisms or approaches to measuring the results of these kinds of personalization efforts?
We use a A/B Testing where we will make a change to the website, like, we will update our algorithm and we will send some of the customers down the, a channel, which is the old experience. And some customers down, the B Channel, which is the new experience.
And using statistics, we can find out whether or not the customers who are getting the new product or new experience convert at a higher rate, or spend more money per purchase or have a higher revenue and total and we can figure out the statistical significance of So that when we actually decide to roll out the change, we're confident that it's actually going to improve the experience for customers.
So it's exciting. It's a bit like scientific experimentation in this experimentation, how much is managed by the retail shop owner versus? How much is managed by algo Lea behind the scenes, we have A/B Testing built into everything that we do on the platform because we think it's just like one of the highest velocity ways of improving. Proving your experience. So it's definitely built into Al kolya, we can run manage all the A/B experiments for you, show you the data.
So you feel confidence in making changes Are there specific metrics that reflect customer Revenue but also customer loyalty and customer lifetime value. There are a lot of really important metrics that you need to keep track of when you're running an online business and it really depends on kind of where in the buying funnel, I think you are. So, for example, when a customer first arrives in the site, it's important to look at the bounce rate. How many clicks do they get into
the product before they? It will experience it. Whereas, if someone's made it all the way to a landing page, for example, you probably want to be more focused on the conversion rate and whether they're actually going to check out and buy something and then after they've actually bought something, you really want to be looking at that lifetime value number. How often do they come back to
the website? Visit again, one of the things that I think is extremely important, particularly for search is the Mission it, which someone has clicked on a result when given a set of search results. If you have, let's say, 10 rows worth of search results, the results that appear on the very first row will always get clicked on a far higher rate than the ones that appear on the tenth row. So I really think that making sure that the products that you're getting into that first
row. We're second row are extremely relevant. We see it makes a big difference. All of these very granular. Sets of reference data, become the building blocks, or the components of understanding the consumer, and then you can respond, you need to understand the products really well that you're selling. And the kind of options you have
to present. Secondly, you have to understand the Shopper who turns up through personalization through profile building through, looking at all, their past interactions, and then thirdly, you need to understand and Real-time the things that they're telling you that they're looking for the
intent. How do you manage to different kinds of Shoppers you have folks who show up and they leisurely want to browse your catalog and then you have other people who just, you know, I don't have any time and I just need to buy this product and if you don't have this product right now, I'm going away. And if you do have it, I'm going to buy. There are a couple of shopping
modes. The first one which obviously you need to be. Incredibly good at capturing a high intent, Shopper is come to buy specific product and you need to do that with Incredible search results and really great ranking of those results. Then you have a second set of Shoppers who really enjoy the experience of coming to a site and being inspired and discovering this site has to offer. And these are Shoppers where you really want to create a browse experience which is far more
interactive and far more. Or inspirational. So I'll tell you at the moment. Most sites have a browse experience which is something along the lines of, okay, a customer clicks on. The dress category, we have 30,000 dresses, you know, give them 100 Pages worth of dresses and order that by the most popular and it's just like entirely overwhelming. And often the most popular products are some of the least inspirational Shawn, where is
search going over the next few? Here's one of the big things is going to happen to search. We talked about how vectors and large language models are really transforming the way that we searched. We're not just matching keywords anymore. We're actually understanding customers understanding the concepts and coming up with much better matching algorithms, but I think one other major change is going to be the way that we have more conversational
approach to shopping. So when you think about the offline shopping experience off, When people go into a physical retail store because they want to get some assistance and they want to talk to someone who has some expert knowledge that used to be an experience. That wasn't very good online, it's very static. It's like here just read the
information. You figure it out for yourself but with the power of chap GPT and these large language models, we're going to be able to have much more expert, personal assistant like conversations at scale. Sean what should eCommerce retailers? Do now to take advantage of all of these capabilities you've
been describing. So I think there are three main things that eCommerce operator should be thinking about the first is the vendors, they work with, they should be working with their existing vendor today to take advantage of some of the AI capabilities that are coming or to you know select or add vendors. Who have these AI capabilities. The second thing is that I think they really need to focus on
their own analytics. So really capturing all the data correctly about their Customers whether that's clicks and conversion data. But also like making sure the capture the cookie IDs and who's logged in ETC. So that you can personalize the experience. And then thirdly, I think they should be thinking about the metrics that matter to them as a business. So they can understand how the AI algorithms are actually creating a more sustainable profitable and long-term loyal.
Customer base. We've been talking with Sean Milani, Chief technology officer of algo, Leah, For more information, check out www.google.com.