The Next Wave in Recommendation Systems?

While some internet privacy experts fret over use of cookies and web profiles for targeted advertising, the quest for personalization is about to go much deeper as web companies create new profiling techniques based on the science of influence.

Behavioral targeting on the web using cookies, http referrer data, registered user accounts and more is about to be significantly enhanced says columnist Eli Pariser.  In the May 2011 issue of Wired Magazine, in an article titled “Mind Reading”, Pariser discusses how website recommendation and targeting algorithms; “analyze our consumption patterns and use that information to figure out (what to pitch us next).”   However, Parser notes that the next chapter for recommendation systems is to discern the best approach in influencing online shoppers to buy.

In the article, Pariser cites an experiment by a doctoral student at Stanford where online shopping sites attempted to not only track clicks and items of interest, but also determine the best way to pitch a product. For example, pitches would alternate between an “Appeals to Authority”; as in someone you respect says you’ll like this product to “Social Proof”—everyone’s buying this product, so should you!

Taking a cue from the work completed by Dr. Robert Cialdini it appears that the next wave in recommendation algorithms is to learn our “decision triggers”, or the best way to persuade us to act. In his book “Influence: Science and Practice”, Cialdini documented six decision triggers of consistency, reciprocation, social proof, liking, authority and scarcity as mental shortcuts that help humans deal with the “richness and intricacy of the outside environment.”

Getting back to the Wired Magazine article, Eli Pariser says this means that websites will hone in on the best pitch for a particular online consumer and –if effective—continue to use it.  To illustrate this concept, Pariser says; “If you respond a few times to a 50% off in the next ten minutes deal, you could find yourself surfing a web filled with blaring red headlines and countdown clocks.”

Of course, shoppers buy in various ways and not always in the same manner. However, the work of Robert Cialdini shows that in the messy and complicated lives of most consumers that mental shortcuts help with the daily deluge of information. Therefore, this new approach of recommendation systems using principles of psychology in tailoring the right way to “pitch” online shoppers, might just work.

There’s no doubt that recommendation systems already take into account principles of social proof and liking, but there’s a lot more room for improvement, especially other areas that Cialdini has researched. The answer to ‘why we buy’ is about to be taken to a whole new level.

Questions:

  • What’s your take on this next development in recommendation systems? Benefit or too much “Big Brother”?
  • Are you moved by “act now” exhortations? What persuasion technique/s work best on you?

Implications of Computers Reading the News (News Analytics)

Wall Street analysts and traders have a new weapon at their disposal: news analytics. In an effort to keep up with the deluge of news, events and alerts, some investment firms are turning to machines to read and score news for sentiment and word counts. This information is then inserted into trading models, which may be responsible for a huge buy or sell in your company’s stock. Marketers, with machines reading news and making buy/sell decisions in near real time, what are the implications for your PR, communications, and social media strategies?

Wall Street analysts and traders have long believed that stock prices jump on the release of positive and/or negative news. But the sheer number of news sources and volume makes comprehension a daunting task for individual traders. Adding insult to injury, most of the data in the world is unstructured, meaning that it is not in a database and may consist of text, JPEG images, flash videos, etc. So, interpreting the “meaning” of unstructured data often takes too much time.

Enter analytics. With the assumption that news flow is a good indicator of trading volume and stock price volatility, traders are using real-time data feeds, advanced algorithms, and computer power to digest and execute trades on “news” in sub-seconds.Machines are reading press releases, news stories, analyst reports, stock alerts, and more to gauge the sentiment, relevance, novelty, and volume of news. And trading firms are busy designing models to forecast stock prices based on historical news volumes.

Machines reading the news are scanning for two key criteriasentiment and counts.

Let’s tackle sentiment first. Reading for sentiment, algorithms are scanning news looking for key phrases such as “better than expected” or other verbiage. They score news on how relevant a news item is to your particular company, whether the news is unique, the source of news (key analyst vs. small time shop), and what the specific headline says.

When examining counts, news algorithms seek how many times a key phrase shows up in the news, how often that key phrase is used over a time period (e.g., last 24 hours, past three days, and even how many articles were placed over a specified time frame to discern news volume.

This trend has significant implications for marketing and PR professionals. While we may not know the “weighting” system of what is most important to these algorithms (e.g., word counts might be more important than uniqueness), we should definitely bear in mind that in addition to human readers, we’ll now have to contend with machines.

At some point, most marketers have solely written, edited or approved a corporate press release. However, with machines starting to “read” the news items, your communication strategies might need more than a simple tweak. Ultimately, this means that press releases may need to be optimized for machine scanning. In addition, as these algorithms monitor news feeds from analysts, commentators, and other news professionals, one strategy might be doubling down on press and analyst relations to help shape content before the computers read it.

Machines are now reading the news and trading on what they discern. And news analytics isn’t just for large cap stocks! In fact, any company that trades on an exchange is fair game. Knowing this, your company’s stock price might go significantly up or down depending on your future marketing, social media and PR strategies. Fortunately news analytics is in the early adopter phase, but if there’s money to be made then surely this will be a growing trend.

Questions:

  • Other than those listed above, what are the implications of machines reading the news?
  • What might be some PR, marketing, and social media strategies to take advantage of this trend?