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 dependency injection to test functions that would access external data sources. It’s a testament to the effectiveness of the pattern that it lasted so long. However, as our code base has grown over these years, we eventually started to run into some growing pains associated with the way we were doing things. Read More
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.
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.
For those of you still humming Christmas jingles and eagerly waiting until next year when you can belt them out again, here’s a little history about your favorite good-hearted reindeer. Did you know that the most famous reindeer of all is a 1939 creation of an advertising copywriter?
The idea for Rudolph took flight one foggy winter’s night in 1939, after the New Year. Retailer Montgomery Ward had a tradition of giving away children’s books as a holiday promotion, but for the 1939 Christmas season, the company decided to create one in-house to save money. Robert May, a 33 year old copywriter for the retailer’s catalogs, was known for sharing rhymes at the holiday party. This year, he was tasked by management to create a story about a lovable animal. Read More
On November 10, 1969, television viewers were introduced to “Sesame Street”. In the almost 50 years since, the series has become one of television’s most-watched and most iconic programs, and not just for kids. With 90 million graduates in the US alone, adults and parents love it too. And it has won more Emmys (159) than any other show in history.
The series began in 1969 as a revolutionary idea: use TV to help kids learn. At the time, an estimated 97% of American homes had a television set, and preschoolers were watching on average 27 hours of TV each week. Television producer Joan Ganz Cooney set out to create a show for kids that would “master the addictive qualities of television and do something good with them” – such as prepare them for school. Read More
After a long, hot summer, we look forward to sweater weather, splurging on their favorite candy, costumes, and decorating for the Halloween season. And of course, bingeing on some good Halloween-themed TV.
According to the National Retail Federation (NRF), American consumer spending for this Halloween is forecast to reach a record $9.1B, up from $8.4 billion in 2016. Seven out of ten plan to celebrate Halloween this year by dressing up, handing out candy, and decorating our homes and offices.
The unprecedented fury of Hurricanes Harvey, Irma, and Maria caused power outages, flooding, and hundreds of millions of dollars in damage. While this season’s aggressive hurricane season has broken weather-related records left and right, it’s also impacted something a little closer to our industry: television.
When Irma struck Florida as a Category 4 hurricane, it left 6 million people without power in Florida and drove others towards watching the weather news. The Weather Channel kicked into “severe mode,” broadcasting live around the clock for several days around each of the back-too-back storms. It was the only network to do so, which was reflected in its ratings. Read More
“The Muppet Show.” The original one, from the late 1970s and early 1980s. Only the most sensational, inspirational, celebrational, muppetational show ever. I did not come up with that myself. Those are lyrics from the opening credits of the show.
The original “Muppet Show” premiered in September 1976 in the UK. Creator Jim Henson took his idea to the US TV networks: ABC, CBS, and NBC. US network executives unanimously praised his work, but were not convinced a puppet show could pull ratings in prime time. Henson created two pilots, which aired on ABC. Neither brought in good ratings, so ABC passed on the series. Read More
It’s the end of August, which means that kids all over the country are soaking in the last of the summer sunshine and gearing up for school starting up again. If you grew up in the ’80s and ’90s, an important part of the school year was Drug Abuse Resistance Education – also known as D.A.R.E.
D.A.R.E. began as a small program in Los Angeles in the early ’80s, but grew to a major, national campaign in schools. At it’s peak, D.A.R.E. was implemented in 75% of American schools. Read More
Archibald Query. You may not know his name, but if you have spent much time in New England, there is a very good chance you know a product he sold for a few short years leading up to World War I.
One hundred years ago, beginning in 1917, he cooked batches of melted marshmallows at home and sold them door-to-door in his neighborhood in Somerville, MA. Sadly, a World War I sugar shortage ended his enterprise. In 1920, Query sold his recipe to Massachusetts-based candymakers H. Allen Durkee and Fred Mower, for $500. Read More