Analyzing Alexa Skills During a Hurricane
How the Hurricane Center skill survived the eye of the storm
One of the Alexa features that customers are still learning about is the ability to run custom skills — or skills that are independently developed and enabled on the platform.
Just like at the start of the iPhone revolution (circa 2007–8) when people first focused on the ability to play music AND make voice calls from a first generation mobile phone, behind the scenes was the advent of the app store. There were apps available during the initial launch, however it took a few years for the market to really explode.
This year Amazon has already gone from 500 custom skills in the store to 3000, and I’d guess that it will be easily 5000 by the end of the year — 10X growth, and this will provide content for the store to curate in the time ahead.
Amazon Provides Built-In Alexa Analytics
Built into the skill development platform is a basic set of analytics, but require absolutely no effort by the developer. Like many things on the platform, it’s evolving, and I’d expect to see even more features as time goes on (remember — we’re still at 2007 era iPhone App Store.)
If you’re not familiar with this capability, here’s a brief overview of what the developer console looks like. This is where you define the voice interaction rules that a custom skill uses. Within the console, it’s under Alexa then under the Alexa Skills Kit tab.
Case Study: Hurricane Center Skill
Earlier this year I wrote a custom skill that’s available on Alexa to help notify people of storm data available through the NOAA. During a Tropical Storm or Hurricane, detailed forecasts are available online, and I used Alexa’s voice capabilities to read the information when prompted.
More details on the Hurricane Center skill are available on Hackster.
As you can imagine, the skill normally has a fairly low usage other than for storm enthusiasts looking to hear the current years storm names. This Fall it has seen a few spikes in utilization, unsurprisingly based on when the skill is most relevant, and hopefully does the most community good — when a storm approaches.
Analyzing the Impact of Hurricane Matthew
Last month saw a devastating storm go through the Caribbean, impacting many lives in Haiti, Cuba, and Florida, then again creating terrible floods in the Southeastern United States.
Suddenly the ability to have this critical information became important, and utilization of the skill took off. It’s a great opportunity to highlight the capabilities of the analytic platform as it highlights what level of data is captured.
Below is a screenshot of two key metrics for a Skill on Alexa, Utterances (number of times a user has talked to your skill) and Unique Customers. The online reporting tool enables looking at the data on a hourly, daily, or weekly period, very similar to other click/page view data tools available for the text based internet.
Trending Skills — “Alexa, Open Hurricane Center”
Given the attention paid to the Hurricane Center Skill during the period of Matthew, I found it ended up on the top spot for a while.
There’s a correlation to other custom skills written on the platform. Amazon is running analytics on what skills customers are using, and presenting it in the app for others in the community to see.
Summary
It’s still early days for the Alexa platform, and a great foundation is being built. If you haven’t tried writing a custom skill, I’d recommend doing so, and you’ll be surprised how much of the ecosystem is already being developed around you.
If you’re interested in learning more, please see part II that takes analytics further, and explores how to track detail within the application.
If you are interested in developing your own Alexa custom skill, A Cloud Guru has courses available covering all AWS technologies, including Alexa.
A Note From A Cloud Guru
The events that unfolded earlier this month as Hurricane Matthew ripped through the Caribbean has left families homeless and in desperate need of shelter, food and clean water.
A Cloud Guru is proud to have supported the Red Cross Hurricane Matthew Appeal, and would encourage anyone who can, to support their local charities in providing much needed relief to the area.
If you do one thing, then please donate to a Hurricane Matthew relief fund, if you do two things, then ask a friend or colleague to do the same. Thanks.
Terren Peterson is an experienced technology executive with over twenty years of experience in consulting, start-up, and large corporate environments. He is currently the VP of Cloud Engineering for the Retail and Direct Bank Business at Capital One.
Terren is currently developing interactive voice applications using the Alexa platform. He has created multiple Alexa skills. Most recently, he integrated Alexa Voice Service with a Raspberry Pi to create Roxie, the voice-activated pitching machine that won first place in the Best ASK with Raspberry Pi segment of Alexa’s Internet of Voice Challenge on Hackster.io. Terren is now experimenting with the analytics capabilities of Alexa to understand and improve skill usage.
Terren holds a Bachelor of Science in Electrical Engineering from the University of Illinois at Urbana-Champaign. He was the founder of the Digital Campus Lab for Capital One at the UIUC Research Park, and serves on the board of the Hoeft Technology & Management Program. Terren also holds both Architect and Developer AWS Certifications.
