Overview

The Smart Metrics with Dynamic Thresholds Template allows for applying statistical operations to analyze and understand the characteristics of datasets.

How to

Available operations

Normalised Average

It's an average value adjusted relative to value range of [0;1]. It's often used to make data from different sources or categories comparable. It's also useful for clients who would like to keep the real values of data compares private, yet they still want to monitor the trends of their time series.

Example use cases

• A large international retail enterprise faces challenges in managing its inventory efficiently. Different regions have varying demand patterns for products, influenced by factors. The company aims to optimize its stock levels across all stores, therefore, they collect sales data from each store, focusing on key metrics like the number of units sold per product category. Since sales volumes can vary significantly due to store size, location, and regional market size, the raw data cannot be directly compared across stores. The company uses normalized average data to create a level playing field for comparison.

Sum

It refers to the total value obtained by adding all the individual values. It's a basic but essential statistical measure used to aggregate data, providing a simple overview of the total magnitude of the values being monitored.

Distinct Count

It's the count of unique values. It's used to determine the number of different values in a set, ignoring duplicates, identifying the variety within a dataset.

Example

Identify the number of unique products sold or individual customers.

Max (Maximum)

It identifies the largest value in a set. It's used to identify the upper extreme or the highest occurrence in a set of values.

Example

Show the maximum sales achieved in a month.

Min (Minimum)

It identifies smallest value in a set. It indicates the lowest point or the smallest occurrence within a set of values.

Example

Identify the lowest transaction amount within a day.

Average (Mean)

It's a central value calculated by summing all the values in a set and then dividing by the number of values. It provides a central tendency of the data, giving an overview of the typical value in the dataset.

Examples

• A restaurant - an average total amount of a bill per a day of a week.
• A grocery store chain - an average amount of daily sales, grouped by a city district and product type.

Variance

It measures how far each number in the set is from the Mean (Average) and thus from every other number in the set. Precisely, it's the average of the squared deviations from the Mean. It's a useful way of quantifying the amount of spread or dispersion in a dataset.

A high variance indicates that the data points are spread out widely around the mean, and a low variance indicates that they are clustered closely.

Example

Identifying a variance of the amount spent per person per a restaurant bill may inform you about the variety in your client profiles.

Standard Deviation

It's a measure that quantifies the amount of variation or dispersion in a set of values.

A low standard deviation means that the values tend to be close to the mean, while a high standard deviation means that the values are spread out over a wider range.

Quantile

It's a measure that divides a dataset into equal-sized, ordered subsets. Common quantiles include quartiles (dividing into four parts), deciles (ten parts), and percentiles (hundred parts). Quantiles are useful in understanding the distribution and spread of data, such as identifying the median (50th percentile), which divides the dataset into two equal halves.