Location ranking in real time

Location Ranking

Location Ranking

Locations map

In the image above, Anchor Location generated 30 signals. Conjugate Location 1, located 7mi northwest to Anchor generated 10 and Conjugate Location 2, located 1.5mi north generated 8. Probabilistic radius therefore is:

(30 · 0 + 10 · 7 + 8 · 1.5 +….) / (30 + 8 + 10 +…) The first term in the numerator is 30 · 0 since distance from Anchor to itself is zero.

Bear with me, it’s worth it! Next, let us present this data on a visual chart, in order to build a Probabilistic Radius:

Location data provided with location Technology

Each line on the “location distance” chart represents a single day of data, and describes cumulative distribution function of probabilistic radii. This means that for most location points the device did not move more than 60 – 100 miles during an hour. The hypothesis is that locations with an extremely high radius generate noise in the system. Those who have a consistently high radius are considered “Bad”.

OK, but how do we define “consistency”? Consistency, for the sake of our discussion, is an event having a high probability to happen in any given time frame.

Another thing we need to define is “high radius”, or threshold above which probabilistic radius is said to be high. We shall not give this threshold a numerical value at the moment, and rather just denote it as . Later we shall show, that it is more a continuous interval than just a number.

Lets call a location which has radius above  on a specific day as “Sparse”, and so we are able to formulate our goal in a probabilistic fashion:

The days when we observe signals from the location, are called “observations”, and those days when the location is Sparse, are called “successes”. Once the proportion of such “successes” reaches some threshold, the location is called “Bad”. This is clearly a Binomial process with probability  – a probability that we shall try to estimate using Bayesian methods. Indeed, for every location  the probability of location  being Sparse  times out of  , given  is Binomial:

In a nutshell, Bayesian learning is about having some prior probabilities for events which are updated as new information becomes available. The updated probabilities are called “posterior”. It is reasonable, that a location which has a probabilistic radius of 300 miles should probably contribute more to the posterior probability, than the one having 70 miles, on any given day. Using statistical modelling (Beta-Binomial fitting) we’ve managed to establish the functional relationship between probabilistic radius and “learning rate”. That relationship is defined through coefficients of  function. So, for every threshold radius , we say there is 

Alpha&Beta Coefficients

The higher Probabilistic Radius is, the less “successes” we need to establish that the location is a “Bad” one.

Indeed, we can describe  and  as function of  , call them  and  respectively:

We then consider location  we observed  times (days) in the period  which had radius over 100 miles at least once. Define the following:

For every observation  where the radius  was over 100 miles,  is the respective  . Then calculate average  where  is the number of times location had radius over 100km. In the same fashion we get .

Now, according to Bayes, the posterior mean for probability of a location  being Sparse:

, where  is number of times the location was observed with radius > 100, and  is total number of observations of location  in period 

Where

So, we have now some locations tagged as “high quality” and others as “low quality”. Using this tagging, we can calculate for each mobile app, the proportion of signals coming from each location quality type, and rank the data vendor (e.g.: apps and bidstream providing the data) according this metric.

Voila! To conclude, we have seen how by leveraging machine learning, we put in place a mechanism that ensures that we use only the highest quality of data for generating actionable insights. The algorithm “cleans” the location stream of data in a self learning way, taking almost no initial inputs, and by that refrains from placing bids on bad locations and works as a metric for the quality of location data.

Logo Polaris

Want to look
under the hood?

 Semeon Balagula
Semeon Balagula

Data Scientist at Ubimo

Share on linkedin
Share on twitter
Share on facebook
Kinetic and Ubimo WPP press release
News

Ubimo Location Intelligence Allows Kinetic to Connect the Digital and Physical Worlds for Out-of-Home (OOH) Advertisers

Ubimo Bolsters Kinetic’s Ability to Elevate […]

ran ben-yair martech interview
News

MarTech Interview with Ran Ben-Yair, CEO and Co-Founder at Ubimo

The MTS Martech Interview Series is a fun Q&A style chat with martech leaders.

Get the latest in
Location Intelligence

Subscribe to the blog

TSX Broadway - Times Square Billboard
Articles & Research

Who should advertise on the new Times Square billboard at TSX Broadway?

We used Ubimo’s Polaris technology to analyze the foot traffic to Time Square and reveal insights about the audience around the new 46-story billboard.

Weather Marketing: Using Foot Traffic Insights in Business Strategies
Articles & Research

Weather Marketing: Using Foot Traffic Insights in Business Strategies

What are the effects of rain, snow, and extreme cold on real-world behavior?

Adweek article on weather infographic foot traffic
News

Infographic: How Rainy, Snowy and Super Cold Days Affect Foot Traffic

With patterns getting more extreme, brands across verticals need to pay attention.