Happy Holidays from Quintura International

December 18th, 2008 by
Posted in Alts, CEO Views, Debates, Unique Interfaces, Updates | No Comments »

Quintura has just added to their Language Localization: they now have French, Italian and Spanish morphology engines, in addition to the existing English, German, and Russian systems, producing more contextually accurate search results in a variety of languages and geographical locations.

Quintura CEO Yakov Sadchikov also reported,”We are announcing new tools and features of our hosted, visual-based site search and analytics solution, Quintura Site Search. The new features, which shall help online publishers to boost Click-Through-Rates (CTR) on both banners and search result links, include:

- Search Cloud Images: a new interface enables web publishers to embed images and banners (i.e. brand logos and advertisements) in the search cloud. When users mouse over an icon or search term, it expands into a banner, dramatically increasing the click-through rate in tests.

- Icon Blink: To attract users to images within the search cloud, we offer publishers customizable special effects, including blinking icons, to help boost Click-Through -Rates.

- Standalone Search Bar Option: The stand-alone search bar enables publishers to link Quintura Site Search to a separate web-page, so that when search terms are entered, a new window opens, displaying the full-range of search results.

- Color Customization – Additional color options allow web publishers to customize all aspects of the site search display, to match their web-site.

Source: Quintura Blog (Quintura is a sponsor of ours)

New podcast – OrganizedWisdom and Kosmix

July 24th, 2008 by
Posted in CEO Views, Debates, Verticals | No Comments »



Man vs. Machine.It’s the Ultimate Conundrum of Our Generation.

Hear this exciting new podcast from AltSearchEngines featuring a wide-ranging exchange of views from Venky Harinarayan of Kosmix (a sponsor) and Steven Krein of OrganizedWisdom as they debate the pros and cons of human-powered vs. algorithmic approaches to Search, particularly within the Health vertical (although Kosmix is now Horizontal).  Moderated by yours truly.

icon for podpress  Podcast 34:21m: Play Now | Play in Popup | Download

Rated PG-13

Implicit and Explicit Personalization in Search

May 21st, 2008 by
Posted in Debates, Guest Authors | 1 Comment »

Starring Exalead

and SurfCanyon



What are the weaknesses of the major search engines that you are trying to overcome?

In 2007, we conducted a study with 1000 Internet users, and we learned that 1 in 5 users felt overwhelmed by the volume of results their searches returned, and that 1 in 2 users never ventured beyond the first page of results. Given the massive amount of information available on the Internet, it’s distressing to know so many users are abandoning their quests when all they need and more is no doubt available. One has to ask, “Is this hit-or-miss keyword approach the best choice for accessing the richness of the Web?” It’s an especially pertinent question given that on major engines the first page of results is often dominated by spam sites and irrelevant commercial pitches, all pushed to the top of the heap by armies of search engine marketing gurus.

Since its creation in 2000, Exalead has striven to provide it users with an alternative path for exploring the Internet, to protect Internet users’ freedom of choice. To keep the massive amount of information users face both on the Web and at the office accessible and intelligible, we offer ample yet utterly simple tools for efficiently navigating and refining results and enjoyably exploring content. Traditional search engines, on the other hand, don’t give users a choice beyond simply clicking < Next > to move on to the next page in an infinite laundry list. However, we’ve been highly pleased to see that our approach, which we call “Search by Serendipity,” is being taken up bit by bit by the heavyweights.


For all but the simplest navigational searches, too much time is spent trying to find the magic query that yields the desired information on the first page of search results. The search engine should actively work with the user to help them find what they need.


How do you define both explicit and implicit personalization?
With explicit personalization, the user in the driver’s seat. Within the limits of the available tools, users can customize and filter resources on a site in the manner that best suits their needs.

With implicit personalization, it is the site itself that adapts and conforms independently to the needs of the user. It can automatically adapt its resources to the needs of a user (whether individually or as part of a user group) based on the user’s profile and prior behavior.

Our search platform incorporates elements of both types of personalization. Through our public Web engine, we propose a wealth of explicit personalization options for our users, responding as effectively as we can to the heterogeneity of the Web and Web users. For B2C portals deploying our search engine on their own sites, we offer a number of implicit personalization tools as well. These types of tools are best suited to a more homogeneous audience and content base, with the expectations and needs of users being easier to identify-and hence leverage-in the quest for an improved user experience.


Speretta and Gauch wrote “Personalization is the process of presenting the right information to the right user at the right time.” Explicit and implicit personalization are two non-exclusive and complementary implementations.

Explicit personalization specifically asks the user to provide more information about their information need(s). This information is sometimes gathered through long-term general interest surveys (e.g. “what are your hobbies, what is your profession, where do you live?”). For specific information seeking tasks, explicit personalization sometimes asks the user to narrow the search via drill-down menus or by selecting information clusters. In classical information retrieval research, explicit relevance feedback is a technique where the searcher is asked to manually rate documents they have seen in order to more accurately fetch additional documents. Information directly gathered from the user is very powerful for tailoring a search session to the specific user.

Implicit personalization relies on the more ambiguous but more easily obtained history of user behavior to indirectly infer the user’s information need(s). Implicit personalization can be long term (e.g. a person’s hobbies can often be inferred from the web sites they visit repeatedly) or short term (a person’s immediate information need can be inferred from their current actions and context). Implicit personalization can also be collective (e.g. your friends like this so you may be interested in it). Although each user action is only weakly correlated with their long-term interests, the combination of multiple weak signals can lead to very powerful inferences. Properly interpreted, user behavior can lead to strong conclusions about the user’s short-term interests.

What are some popular examples?

Exalead.com is a good example of explicit personalization. All users are presented with the same result sets based on their query keywords, but the presentation makes extended use of keyword clustering to allow users to personalize these result sets based on their needs and interests. We deployed clustering in advance of Ask, and even Google, setting trends in this as well as other areas of Web search technology.

An example of implicit personalization is Last.fm. Last.fm shows that the implicit web is already a reality. Last.fm recommends new music to a user by independently analyzing the user’s existing library of favorite artists. Our purchases, our navigation histories and our search queries feed these types of recommendation engines and can help them refine the World Wide Web for us.

In the context of search, popular examples of explicit personalization are geo-targeting through IP addresses (e.g. if you search for “Ford” he advertisements will often be for local car dealers), related query suggestion (Yahoo! Search Suggest), categorical and hierarchical rill-down (Exalead, Clusty, Endeca, etc.), and explicit user profiling (when Netflix asks you to rank movies that you have seen).

Implicit personalization is used by Google (when you have activated the option) to provide a few search results that take into account your rowsing history. Amazon suggestions are based on implicit personalization although the suggestions are often humorous if you are like me and share an account with your spouse. Surf Canyon is the first company to provide real-time implicit personalization.

What are some of the major advantages and disadvantages of explicit personalization?

The freedom to explore, a uniform user experience. When resources are not filtered according to a user’s prior actions, then that user retains total liberty to explore and discover the complete universe of content available to them. A standardized, non-personalized presentation of resources also constitutes a shared, even egalitarian experience, with each click guiding users to the same results. On the other hand, leaving personalization options solely in the hands of the user can make it more difficult for him or her to fulfill their needs because the system cannot capitalize on a user’s prior actions to help divine their intentions and guide them through what is often an overwhelming amount of information.


The advantage of explicit personalization is that the information is unambiguous. When the user selects a related query or chooses a category among the possibilities presented, the search becomes much more accurate.

The largest hurdle for explicit personalization is that it requires additional work on the part of the user. Web users are overwhelmed by requests for our attention and often don’t want to exert additional effort even if it provides real benefit.

Another major disadvantage is that a user might not be fully cognizant of what they are looking for. If I am using a search engine with categorization, I might end up in the wrong category before I know enough to select the correct category. Even worse, any system that requires the user to explicitly profile themselves is susceptible to people describing who they want to be rather than who they are. As Jason Fry wrote in the Wall Street Journal, “…we lie — and never more effectively than when we’re lying to ourselves. My dissatisfaction with Amazon’s recommendations may have more to do with my view of myself than it does with Amazon’s engine: I fancy myself a reader of contemporary literature and history books, but I mostly buy “Star Wars” novels and “Curious George” books for my kid.”

What are some of the major advantages and disadvantages with implicit personalization?


This interesting approach points to one of the great paradoxes of the Web as revealed by our 2007 study: while 80% of the participants expressed a desire for personalized content, 50% evinced a strong resistance to divulging personal information in exchange.

We think implicit personalization is not well adapted for use in general Web search, if it is offered in isolation. The world of the Internet is infinite and deeply heterogeneous, and the behaviors of individual users are not really predictable. If I search on “leopard,” am I looking for a picture for my kid’s school report, or for information on the latest Mac OS?

On the other hand, the use of implicit personalization is very interesting in more constrained contexts. Our enterprise search software for portals (e-commerce, community sites, content portals, etc.) provide the intelligence needed to deploy implicit personalization and therefore to improve the user experience and augment site revenue.

Of course, implicit personalization raises privacy concerns. Users are rightly concerned as to whether the data they provide or their patterns of navigation for a particular site will be exploited in an unwelcome manner in another context.


The major advantage of implicit personalization is that it requires no additional effort on the part of the user. When implemented properly it can be very effective in providing accurate recommendations to the user.

The major disadvantage of implicit personalization is that it can sometimes make incorrect inferences, especially when the data is sparse or when the user context changes. My long-term interests may be at odds with my short term information needs. As an example, if I search for “Giants Stadium” and hail from San Francisco I am much more likely interested in the place where San Francisco Giants play (I have forgotten the stadium ame since they seem to have a new sponsor every year). Next fall, however, I might find myself in New York and interested in the parking at the Meadowlands.

Surf Canyon does implicit personalization in real time, and the sparse data problem is something we work to overcome. Fortunately, for the most difficult searches we often have the greatest amount of user behavior data and can therefore be of greatest benefit.

Which has the greatest potential to improve the search experience?


They both have great potential to improve the search experience, but only if they are always presented in a transparent manner, with the user retaining the right to choose one type or the other according to the usage context. Again, our approach to Web search rests on leaving choice in the hands of the user, and on respect for users’ privacy.


Both forms of personalization have great potential for improving the search experience, and even more so if used together! For the majority of queries, personalization in any form is unnecessary. The search engine has essentially replaced URLs and bookmarks for navigating to websites, and personalization does nothing for these navigational queries. If the user doesn’t end their search session with the first click, implicit Real-time personalization should begin working with the user to help them find what they need. At the same time, explicit personalization options should be made available to further help the search. Different Searches will require different tools. As the volume of web content grows, users will demand access to all of these tools.

The Great Debates: Property Search Engines

January 15th, 2008 by
Posted in Debates | 3 Comments »




Tuesdays on AltSearchEngines we host our Debates, and this week we are pleased to welcome Yannick Laclau of Properazzi and Gary Stewart, CEO of Migoa/Nuroa.  This debate expands upon our earlier interview with Yannik.



1.  Vertical search engines really seem to be taking off, can you just summarize a few of the challenges that are unique to Property/Real Estate Search Engines (as opposed to People Search or Job Search Engines).

There are many challenges, but fundamentally these are the same for search engines in any vertical: finding and adding fresh content; identifying and removing bad content; accounting for duplicate data; processing search queries quickly. If you’ve solved the fundamental problems, then you can apply them to any vertical without too much trouble. Properazzi are already very advanced down this path already in real estate, with technology that indexes 4 million listings from 11,000 different agency websites.

The main challenge for a property search engine is a variation of the general problem faced by many disruptive start-ups: How do you make yourself known and differentiate yourself when there are powerful web 1.0 property incumbents already online? There are obvious differences between property search engines and web 1.0 real estate portals, but how do you convince consumers that they should care? A lot of consumers are already accustomed to behemoth companies like Rightmove in the UK (a listed company with a market cap of more than €1 billion) or Seloger in France (also a listed company with a market cap upwards of €700 million), and these companies have enough money to out-spend us and enough brand recognition to pose a significant entry barrier. In addition, vertical search engines aren’t a particularly viral product like Facebook where customers have an obvious incentive to return every day and share it with all of their friends. 

So getting the customer to the product is the main challenge when there are powerful incumbents with well-established brands who don’t have cutting-edge products but their products are still more-or-less okay for the average Internet user. Once the customer gets to our product, it’s fairly easy for her to understand how a property search engine like nuroa will make her life a lot easier and disrupt her prior real estate search experience. But the main initial challenge is getting her there. Other than that, there are specific problems related to making sure that our results are precise, relevant and exhaustive, which can be a challenge given that the quality of the underlying property web sites in each country are sometimes pretty questionable.

2.  AltSearchEngines has come across seven significant Property Search Engines in your area, and other minor ones. Why such a crowded field? Are you all primarily similar, or fundamentally different?

In the past few years I’ve seen lots of projects in this area, probably motivated by the promise of easy money: just combine real estate (money!) with the Google business model (more money!) with the mashup/search engine template (easy!). So there was economic motivation and a low perceived entry barrier. If anything, I’m surprised there haven’t been many more startups in the field…maybe what’s missing in the mix is some social networking (sexy!)

Vertical search is a good, simple yet intuitive idea that no one was doing it Europe. That companies like News Corp, The New York Times and Sequoia have invested in similar products in the US (and now in Europe) further encourages European entrepreneurs to start similar local projects before the Americans arrive. As for differences among vertical search engines, it all depends on how closely you look. On some level, Google and Yahoo both have search engines, but they are not regarded as the same. Similarly, on a very basic level, we’re all search engines focused on property. But many of us operate in different markets. For example, Globrix is not currently nuroa’s direct competitor. Their market is the UK, and their main competition is in the UK — nuroa is focused currently on Germany and Spain. Each market is a different world with its own rules, home-buying and renting patterns, economic evolution, language, competitors and targets.

Apart from geography, some of us have different objectives. nuroa aims to be profoundly local — Spaniards buying properties in Spain, and Germans buying properties in Germany — whereas Properazzi has a much more international focus and scope from the beginning. On a technical level, we sometimes differ on how we obtain the property ads. Some of us rely more on receiving XML feeds, whereas others focus more on search technology. Then as an empirical matter, there are obviously going to be differences in whose results are more precise and exhaustive with a higher degree of recall, and the breadth and quality of the results will probably be the key differentiator from the consumer’s point of view. And finally, there are “softer” issues like usability and design that also affect the user experience. That being said, I’m pretty sure that we all borrow and learn from one another.

3.  Most of the updates that we receive from your space are larger territories covered, which is natural, but where does it end for you? How much geography do you seek to cover in the end?

The world, of course! Properazzi never made any secret of its ambition to be the platform for the world’s property listings. Since launching in March 2007, Properazzi have been steadily adding new markets, and now cover 50 countries. We’ll continue to add support for further countries in 2008. But geography is not the only axis along which Properazzi are planning to expand near term.

To date, the web 1.0 real estate portals have been quite successful even though they only operate in one geographical market (this goes back to my answer above about whether those of us who currently operate in different markets will necessarily have to compete against one other at some later point). Rightmove’s expansion plan is to cover all of the UK as opposed to just the big cities like London.

For the moment, they’ve felt no need to compete vigorously outside of the UK. Seloger has a similar strategy to increase its penetration in the provinces outside of Paris. As mentioned above, Rightmove has a market cap of more than €1 billion, and Seloger is close with a market cap of more than €700 million. So you can create an interesting business in just one geographical market if you can become the market leader. That being said, our search technology in nuroa is obviously very scalable, so you can easily adapt it to new countries and even to new verticals. As with most things, your limits will depend to some extent on your financing and your ability to execute.

4.  Can you just summarize your business model and how it relates to the financial needs of the real estate agents/brokers, and perhaps even the property searchers and/or sellers?

Our business model is advertising. It’s great for the advertisers because we’re delivering a very high-value audience for much lower cost than they’re used to paying. For property buyers/renters, Properazzi is 100% free, so our model works great for them as well.

We make money via advertising — featured listings, banners, etc. The web 1.0 real estate portals require real estate agents/brokers to pay a set monthly fee to upload a predetermined number of listings regardless of whether the site actually generates leads for the real estate agency. And given that most of these portals only intend to grow within their national boundaries (and some are public companies), the only ways for them to grow are up and out — up, meaning that they will have to raise prices as many have done over the past year, in some cases doubling the prices; and out, meaning out of the big cities where they started and into the more remote provinces within their geographic market.

Nuroa’s model is different — more pay per click than subscription fee: an agency only pays if we send them traffic for a featured listing or some other form of sponsored ad/banner. Agents don’t have to pay us to have their listings show up organically on our site. From the consumers’ perspective, it’s very useful to have all or most of the property ads in nuroa. Classifieds sites are growing like mushrooms as print continues to falter and more traditional media companies move online, and no one has the time or attention span to visit 50 sites to look for her perfect property. A property search engine cuts out all of the unnecessary steps and let’s the user find her dream home in a couple of clicks.

5.  What is your relationship to the major search engines, Google, Yahoo!, et al? Are they your major concern – or are your fellow Property search engines your main rivals for business?

I honestly think it’s too early days to answer this question effectively. As we evolve, it’s just not clear yet who ends up being a partner, a competitor, or simply a “not relevant”. Ask me again in two or three years :)

Our goal is to supplement not supplant Google and the other major search engines. We don’t really see them as our competition. Google had Google Base for a while, but they don’t really seem to have pushed it very hard. And last year TechCrunch reported that Google was in talks to buy SimplyHired, so obviously that means that, if the reports are true, Google sees the opportunity in vertical search and isn’t opposed to purchasing the market-leader in each vertical. That being said, we didn’t start this company hoping to be bought by Google. Not that we’d be opposed to it on principle, but nuroa’s goal is to become the next Rightmove or the next Seloger. And we see our fellow property search engines within our geographical markets as our most immediate competitors.

6.  How do you market your site – drive users to you as opposed to anywhere else?

We dabble in most of the usual marketing type of activities, but work hardest on developing a great product for users so they can remember and return to our site, and recommend it to their friends.

As mentioned above, this is our main challenge. And we take a variety of approaches to marketing our product, though I’d probably prefer not to explain our strategic marketing plan in any great amount of detail. But I can say that it’s a combination of SEO, SEM and viral marketing.

7.  It’s a tradition to say something complimentary about your debate partner.

Migoa: nice integration of flickr and technorati data, and they chose a great city in which to be based.

In the case of Properazzi, I’d say that we learned a lot from them. They launched before we did and provided a key test case for seeing the market’s reaction and adapting our own strategy before launching. They were also the first European vertical search engine to receive funding from a major European VC, so that served as an inspiration to us. 

Debate – Consumer Electronics Search Engines

December 11th, 2007 by
Posted in Debates | 3 Comments »

Tonight’s debate is on the topic of consumer electronics search engines.  Our participants are Robb with Retrevo and Syed from ShoppingVale.

 1.  A consumer wants to buy their spouse a digital camera for Christmas.
Why should they go to your search engine instead of a major search engine or a store’s website?

Each has different problems so let me address them separately. General search engines such as Google or Yahoo return many results but leave it up to the user to sift through them to determine which ones matter. Because general search engines heavily weight referral links most of the results are all pricing engines because many, many sites link to them for price shopping. Great if the shopper already knows the specific product they want but how does that help consumers DISCOVER the right product that isn’t based on just price or a spec list of features consumers don’t understand?

As for starting at a retailer, well unfortunately for them the Internet has significantly disrupted their role of influencing a consumer’s product decision. A single retailer just can’t offer all the products in a given category so they only present a small sub-set of pre-selected brands and models. Retailers just don’t have the depth of products and their information is often a subset of what the manufacturer has available or quite often incorrect when compared to the actual product manufacturer. Further, how does a consumer know the retailer isn’t pushing products the reps are spiffed or give the store the most profit rather than recommending products that best fit the consumer’s needs?

Retrevo goes beyond search and algorithmically ANALYZES information and presents products in a simple, easy to understand assessment that helps them find the right product and feel confident about the product they want to buy. The Retrevo Product Advisor helps consumers discover products that match their interests simply and easily. When a user first lands on the Product Advisor page they see a real-time view of what to expect for the product category. We break each product category into three simple groups – Low-end, Mid-range and High-end. This helps simplify the information for consumers into something they can easily and quickly digest. Not only does it simplify understanding a product category it’s also the ONLY report that changes in real-time to reflect current market conditions. As new products are introduced or price changes occur, our “what to expect” lists adjust automatically. Products that were once rated high-end or mid-range just six months ago may now be mid-range and low-end products. This is the most accurate and up to date view of any consumer electronics product category in the industry.

Consumers can narrow their search by providing input as to their interests. For each product we have generated a profile that gives users the main points (the “gist”) of any product. This allows consumers to quickly understand the pertinent points they should know and assess if a product is a good product to buy or spend time looking at details such as reading full specs, expert reviews and user reviews. Once a consumer has narrowed down to the product or a few products they like, they can use the Deals and Prices feature and find which stores sell the product at the best prices.

The end result is we quickly educate consumers on what to expect in a product category and guide them through the shopping process to help find the right product to buy whether they want to purchase online or visit a brick and mortar retailer. Benefits to the consumer:

• Instantly learn what to expect for any consumer electronics product category.
• Receive objective advice on products to buy that match their needs.
• Save time and effort as Retrevo does the research legwork for them.
• Quickly understand the main points, value and community sentiment on any CE product.

ShoppingVale was created in response to several years of experience working with leading online retailers and analyzing cross-channel consumer behavior.

Consumers generally start by conducting research; reading reviews, buyer guides, specialized websites among other resources. ShoppingVale allows consumers to conduct this research in the manner they prefer. Our search service provides unbiased, unfiltered access to all available information from the top respected resources.

This unfettered access gives the consumer information that is typically unavailable at comparison sites, such as photographs, Video demos, multi-media product tours and other informative product information.

Once a consumer has an idea of the product they are interested in, ShoppingVale provides easy access to the top retailers for real-time information on price and availability.

Unfortunately other shopping engines like Retrevo, Nextag, _Shopping.com_ <http://Shopping.com> provide information that is filtered and pre-packaged. While this presentation may at first look like an excellent way to compare retailers, the information missing is critical for making an informed decision. Let me tell you a personal story that helped me to kick start ShoppingVale. A while back I was looking for a camcorder and I went to a typical shopping comparison engine to compare prices. At first it appeared that several relatively unknown retailers were selling the camcorder $50 cheaper than a brand-name retailer like Amazon. After exiting the comparison site and going directly to each retailer, I discovered to my disappointment that it wasn’t an apples-to-apples comparison that I was originally led to believe. The non-brand name retailers were only offering a bare-bones camcorder; essentials like the battery and cables were being sold separately. In the end, the smaller retailers were more expensive than Amazon, with a more strict return policy.

ShoppingVale addresses this problem by allowing the consumer to see all the details directly, so they are not being led to believe that all offerings are equal. We give consumers unfiltered access to compare, side by side, each retailer. For example, for electronics we provide one-click access to Amazon, Best Buy, Circuit City, Wal-Mart, Target, _Buy.com_ <http://Buy.com>, Dell, Costco, eBay among others.

You can also get the money saving coupons at ShoppingVale, just type in the Product name in our “Looking for Coupons” section and start saving money.

Give it a try, just type in “Sharp lcd hdtv” in ShoppingVale and Retrevo you will see the difference. I will let you be the judge.

2. How do you plan to drive users to your site (how will they find you)?

Because we cover the entire lifecycle of consumer electronics and not just shopping we have relevant content that also helps consumers USE the products they buy or find support. Retrevo primarily focuses on SEO and leverages this content. We will also in the near future include advertising but we’ve been very pleased with our SEO and WoM traffic growth so far this year – especially after our recent launch of the Retrevo Product Advisor.

We are advertising online using adwords from Google, Yahoo & Microsoft. We will be advertising on Facebook and MySpace shortly as well. Also, by consistently providing the best results and experience possible. Customization options further enhance the user’s experience. If we do this, shoppers will find out from referrals of friends, colleagues, etc

3. Within the Vertical of Shopping search engines, what features are unique to your search engine?

a) Real-Time product value assessment – Retrevo is the first and only company to assign an algorithmically derived value to each product in a given category.

b) Real-Time community sentiment assessment – Retrevo is the first and only company to aggregate the total community sentiment from both expert reviews and user reviews into a single sentiment rating.

c) Real-time product range assessment – Retrevo is the first and only company that dynamically assesses the range of a product in a given category.

These key features are possible through Retrevo TrevolysisTM  

The basis of TrevolysisTM is the analysis of all the feature values, prices and sentiments of all products in a given category.  It is based on years of research in pattern recognition combining advanced methods in multivariate Bayesian decision theory, supervised machine learning and mark-to-model valuation techniques.  We first determine the price-feature position of each product by analyzing hundreds of thousands of product features (e.g., viewfinder type for a digital camera) and current prices.  The result of this analysis is a crisp visual presentation and/or textual summarization of a product on a product profile or a category map along price-feature axis.  The distribution of all normalized product feature values is further analyzed to identify clusters of products with common features forming the basis for the Product Class summary. 

We then determine the fair value of each product based on its feature set and our proprietary mark-to-model valuation technique.  A Value Rating is computed for each product that reflects the deviation of current price of that product from its fair value.  Since the market conditions change on a daily basis and new products with new features are introduced frequently, a product’s fair value and Value Rating assessment also changes constantly.  This analysis is completely algorithmic and automated.  It aims to provide a holistic and objective fact-based product evaluation.  The time when the latest analysis was performed is displayed along with the summary.  Users can therefore always get the real-time value assessment of a product.

While the fact-based summary provides a very objective assessment of products based on current market conditions, qualitative information associated with the brand and user/expert opinions play a very important role in users’ buying decisions.  We scour the web for expert and user opinions for a given product and analyze them for sentiment for that product.  A single Community Sentiment Rating is computed for a product based on a weighted combination of the expert and user opinions for that product.  The weighting is computed using a set of proprietary and automated mathematical formulae that not only weights each opinion but also weights the domain of the web site containing the review based on the variation of all (and category-specific) product ratings found associated with that domain.  Our analysis is based on over a million expert and user opinions on the web.  The Sentiment Rating for a product is displayed along with the total number of user and expert opinions that it was computed from.

TrevolysisTM provides the industry’s first comprehensive yet simple to understand summary of a product’s facts and sentiments.  It is the first of its kind presentation of fact-based Value Rating that combined with a qualitative Community Sentiment Rating provides a powerful product assessment tool for shopping.

Consumers get direct, immediate and unbiased access to /all/ the information. This information is real-time so it’s always up to date. Our results are not based on a commission from a particular retailer. We do not filter, based on our personal opinion, the results.

4. What is your relationship, if any, to national brands, retail stores (like BestBuy) or local stores?

Although many retailers will appear in our search results for stores and prices we maintain no direct relationships with any retailers at this time.

To maintain our unbiased approach, we do not partner or any way solicit money from the retailers.

5. What is your relationship, if any, with other alternative search engines?  Any partnerships?

Retrevo does not currently have relationships with any of the alternative search engines. 

We are kick-starting the process of reaching out to alternative search engines. We recognize our unique service provides a great value to the consumer regardless of the venue.

6.  What’s one compliment that you could give your debate partner as we end the debate?

They have aggregated some top retailers and made it easy for me to compare different stores.

There is a lot of visual appeal to the site design they implemented.

Thanks Robb and Syed!  Readers, let them know if you have a question or comment.