Generally e-commerce retailers have grown from a fairly narrow set of product categories (e.g. books for Amazon) to adding more and more diverse categories. This has a dramatic impact on site search quality.
If you consider a simple example, shoes. You only need a couple of facets to filter products to a reasonable set to browse through: gender and size. Now start adding accessories, athletic clothing, and so on, and the results end up getting harder to navigate with generic search terms like "shoe" giving less relevant results (not having the context of the user's intent hurts here).
I tried "shoe" on Amazon, got over 400,000 results with the first item being a shoehorn. It takes a bunch of clicks to deal with that.
This search problem gets worse as catalog sizes grow even bigger. Personalized results help a lot and Amazon seem to fail me with this, they don't do a good job bubbling up the products I buy to the top.
It's a hard problem to solve but it's not going to kill Amazon.
Systems like Solr, elastic search and endeca (out of the box) all assume relevance means keyword frequency in a product page, with some weighting depending of title, description, tag, etc. Delivering relevant results that users might want to purchase requires taking these systems, adding or customizing their NLP techniques, operationalizing historical user search & purchase data to determine intent, personalizing by shopper history, etc.
The challenges of massive heterogenous catalog affect other areas... Chief among them search result personalization… an individual’s gaming purchase history might cause ‘button down’ to return gaming keyboards, rather than oxford shirts, while a pet products purchase history could lead to a search for turkey returning turkey dog food.
The fact that Amazon fails to personalize search results is evidence of the difficulty & opportunity here. The sort of pervasive personalization found in AirBnb, facebook, google are simply out of reach of most ecommerce retailers…
For me, personally, while "Joe's Truck Parts dot com" might do a better job of finding me the floor mats that fit my truck (or the manufacturer) - Amazon already has my credit card on file, and my address, and (for the most part) ships anything I order to my doorstep within two days. So I know I'm not transferring my credit card data to some random, sketchy company who stores it on some Windows 98 server, and takes 2 weeks to ship me my product, and when they finally do ship it, it could take 7 days to get to me.
In either event, I do like to support local business and small business - but I enjoy the convenience and familiarity that Amazon offers...so even if their search isn't the greatest, I'll still be clicking purchase on their site, for the most part.
But you might be surprised to know that many sites for automotive parts are actually operated by the same company. They have different domains, UI skins and marketing campaigns, but they're the same under the hood (so to speak).
For example, compare https://www.carparts.com/ and https://www.usautoparts.net/
I would be annoyed with a coin slot in an elevator that said "insert 25 cents to close doors" and then it did nothing, however.
A magic list that I can add any item to, select a delivery date, and have the backend automatically fulfill each item, at the cheapest price, on time. I want to completely abstract away the concept of a store. I want a to-do list that automatically delivers stuff to me. Additionally, I want a standardized return policy no matter who fulfills it.
I want to be able to say:
- (3) Organic Roma tomatoes
- (6) Sonicare replacement brush heads
- (1) Patagonia Down Sweater, Black, Medium
- (1) Bookshelf assembly service, in-home, 3/16/19
and magically have it fulfilled. One could have a slider to make the tradeoff between speed of fulfillment and cost.
Amazon already sort of does this, but not at the best prices. One would hope that in the magic to-do list model, local retailers would be able to outbid non-local retailers, as their shipping costs would be inherently lower.
Banning the crap sellers would also make search easier. Less duplicate listings.
Maybe I'm alone here, but I have an extreme distaste for personalized search results. I know what I want to see; it's pretty rare search knows what I want to see when it's trying.
Take the "chips" example from the interview--maybe I'm tired of eating the same fucking chips every day. Maybe I just want to know what the most popular options out there are without having to scroll a lot. Not to mention that I have a preference for Pringles, I'm going to type the brand name into the search when I want to find it. (If I'm a dog lover, I don't expect Google to rank dog results first when I type in "animals." I expect information about animals in general.)
There's also been a ton of research done that most consumers do want personalized experiences, will pay more for them, and will be more likely to churn if they don't have them. There's a pretty good list at https://venturebeat.com/2017/08/18/hyper-personalization-mar....
Some examples from that article:
>>> Forrester uncovered the fact that 77 percent of consumers have chosen, recommended, or even paid more for a brand that provides a personalized service or experience.
Accenture found that 75 percent of consumers are more likely to buy when you show you recognize them as an individual and provide recommendations based on their unique wants and needs.
Looking forward to see AI search grow in popularity and become democratized for developers.
Of course, it's not the same, and retailers need to do a hundred other things correctly as well, but there is a lot of data to show that people go where the good search is.
A company which faithfully executed an AI for me, eg looking at every pair of jeans and then using NLP or whatever on the reviews to rank them based on my shopping history and stated preferences, measurements, etc.
In many ways, sites are already stumbling in this direction: they do analyze purchases and so forth, but the level of granularity is poor and the control that the customer has over it is basically non-existent.
But whoever takes the (ironically Amazonian) approach of serving customers with AI (as opposed to using the same tech for marketing at them) is going to win, because they’ll have solved the discoverability problem — which plagues online shopping (and online things generally).
