There are only twelve notes in Western music. Just twelve. And in any Western scale, there are even fewer – just seven notes.

It is surprising how many of us in tech have music alter-egos. I’m guessing it has something to do with how both areas of study result in a challenging combination of art and science. There are rules, there are guidelines, and there is structure – but within those rules, guidelines, and structure, we find creativity, imagination, and inspiration. We strive for elegance amidst the chaos, and many times we find the most interesting things when we examine the 3rd note and the 7th note of a scale.

Just like how 3rds and 7ths in music can add interest to a solo, certain aspects of data can add interest and depth to an analysis. Here are some examples:

Outliers: Outliers are data points that are significantly different from the majority of the data. They can provide valuable insights into the data and can be used to identify trends and patterns that may not be apparent in the main data set. Why does it cost so much money to run that one facility?

Trends: Trends refer to patterns or movements in data over time. They can help identify changes or shifts in behavior and can be used to predict future trends. Trends highlight drift, and drift over time highlight things that might not be readily visible from day to day, week to week, or month to month observation. Why did my no-show rate go from 3% to 5% over the past 6 months?

Relationships: Relationships between variables can reveal correlations and associations that may not be immediately apparent. For example, there may be a relationship between income and education levels or between age and voting behavior. This is where AI shines – finding how non-intuitive variables trend together.

Anomalies: Anomalies refer to unexpected or unusual patterns in the data. They can provide insights into potential issues or problems and can be used to identify areas that may require further investigation. Anomalies are similar to outliers, but the difference is important. Outliers are single data points. In my example above, the outlier is a single department. Expanding on that example, an anomaly would be that one facility was so much more expensive than others because it was in the center of a pandemic hotspot.

By focusing on these aspects of data, just like how musicians focus on 3rds and 7ths to add interest to a solo, you can find the most interesting and valuable insights in your analysis.