Implicit and Explicit Profiles

There are many startups attempting to build content recommendation and curation algorithms. Their approches are varied and range from the simple to the very complex.

I would generally categorize the simple approach as using explicit profiles. Explicit profiles are built by asking directed questions (What are you interests?) and tracking usage (What articles have you read?)

The complex approach is to build implicit profiles. Implicit profiles are based on what you do, but also what you don’t do. This requires a lot more understanding of the content characteristics and mapping them back to the user profile. For example, you have be shown 10 different articles about a specific topic, but you only click on 1 of them. What was the reason you clicked on that specific article? What it the image? author? title? time of day? day of week? device (mobile/tablet/desktop)? What if you already read it from a different source?

Recommendation algorithms are designed to be safe. If you’re on Amazon looking at a book, you won’t be recommend a scooter. It will most likely recommend another book within the same genre and topic. This bodes well for a the explicit profile approach to work without the need a very strong implicit profile.

There are many other issues to overcome with content recommendations and curation, I don’t think implicit profiles will be the main hurdle.

I used the app this weekend and while very basic, it is very useful and the open API will be a valuable resource to anyone looking to build a transit/travel app.

Get the app here https://itunes.apple.com/us/app/id561507659?mt=8

The API is here http://datamine.mta.info/ I have yet to play with it, but from what I remember it was pretty straight forward.

Anyone going to use the data feed for something else beside finding your next train?
I’d love to hear about it. 

http://larrymai.com/i-used-the-app-this-weekend-and-while-very-basic/

Assisted Serendipity

The winner of the content recommendation and curation race will be the first to solve assisted serendipity.

Show me things I didn’t even know I wanted.

This can be a contrasting point of view, background or historical context or just an undiscovered source of information.

The only company that has come close is Pandora and it wasn’t cheap nor easy.

I recently launched a fashion blog, http://sociologyofstyle.com. We’re starting to see some good improvement in our search results position and therefore more organic search traffic.

The chart shows how we’re doing with ALL of the keywords we’ve been associated with. We’re doing even better with the specific keywords we’ve targeted.

We’ve managed to achieve a PageRank of 4 in the short 3 months we’ve been live, for what it’s worth. 

http://larrymai.com/i-recently-launched-a-fashion-blog/

Evolution of Content Discovery Tools

In the beginning, there were a handful of sites where you would go to to seek information (CNN, ESPN, WeatherChannel etc.) As the amount of information grew, companies were developed to help categorize and sort information (Yahoo), then came search engines.

Today, we’ve had a massive shift in the way we consume content. We no longer have to pull or seek out content. The majority of content we consume now is pushed to us via email, Facebook, or Twitter.

As the number of friends and follows grow on the social platforms, the amount of information gushing through multiplies and we’ll need another tool to help sift through all that content.

Fitocracy Blog: Getting Fitocracy Back Online

Fitocracy Blog: Getting Fitocracy Back Online

Brian K Balfour: Achieving The Network Effect: Solving The Chicken Or The Egg

Brian K Balfour: Achieving The Network Effect: Solving The Chicken Or The Egg

The Naive Optimist: I'm tired of the opportunists and their hackathons

The Naive Optimist: I’m tired of the opportunists and their hackathons