April 26, 2018

Cinco de Mayo: More than a Reason to Drink Corona

Cinco de Mayo is around the corner and you are likely to be one of many who have a few Coronas to mark the occasion. Cinco […]
March 29, 2018

Sugar-Coating Easter with Lots of Peanut Butter and Chocolate

Easter eggs come in all sorts of sizes, and of course, colors. My favorites are the ones that are chocolate on the outside and peanut butter […]
March 20, 2018

clypd Adds an Advertising Innovation to its Patent Portfolio

Today we are celebrating a proud achievement at clypd – we were granted a key patent (9,924,210: COMPUTER SYSTEM AND METHOD FOR TARGETING CONTENT TO USERS […]
February 27, 2018

The Amazing Race of Forecast Models

Deal or No Deal To plan for a TV advertising campaign, it is important to have a good understanding of the trend in TV audiences: who […]
February 22, 2018

Wheaties: The Gold Medal Standard

The bright orange box. The proud athlete on the front. One brand has been the dominant symbol of American triumph in sports: Wheaties. Wheaties, then called […]
January 25, 2018

Cindy Crawford Poised to Make a Super Bowl Comeback

For only the second time in its 52-year history, the 2018 Super Bowl will be played in Minneapolis. The last and only other time Minnesota hosted, […]
January 24, 2018

Modular Interface Mocks for Testing

It’s been almost three and a half years since I published “Database Testing Patterns in Go“. The post was about how at clypd we were using […]
January 18, 2018

New Report: Unlocking the Data Behind Targeted Linear TV

Linear TV remains the primary way of reaching mass audiences effectively. According to Nielsen, in Q1 2017, Americans spent over 11 hours per day interacting with electronic media (including TV, radio and digital). The single largest piece of that was linear TV, accounting for nearly five hours. So, if you’re a beer brand, why advertise to Men 21-34 when you can advertise to all beer drinkers 21+? Making TV advertising better using data is to everyone’s advantage: advertisers get a better return, media owners use their inventory more efficiently, and viewers get more relevant ads.
January 10, 2018

Using Algorithms to Improve TV Audience Forecasting

This is the first of a series of blogs around building time-series forecasting models. At clypd, we use forecasting models to help media owners and buyers forecast future TV audiences. A successful forecasting model depends on many factors. In this blog, we focus on algorithms, and how we tap into both modern Machine Learning (ML) models and classical statistics models to take advantage of what both offer. The advancement of Machine Learning and Artificial Intelligence has been creating amazing stories everyday, from the AI assistant and self-driving vehicles to computer programs beating professional Go players. At clypd, we also have lots of success stories of using ML models. With the benefits of better accuracy and better automation, these ML models are an integral part of our forecasting models. At the same time, we also continue to find great value in “conventional” statistics models. So, instead of pitching Data Scientist vs. Statistician, let us look at ML models vs. statistical models, and how we can leverage both types of approaches in building a TV audience forecasting model.