Documentation

Alerts

Even if you have the most sophisticated BI and KPI reporting software on hand, you might have problems to see what is really important. The more dashboards and the more charts you have to track, the harder it might get to have full control of what actually matters and drives your business.

 

datapine helps you to monitor your most important KPIs and informs you automatically as soon as an unexpected event happens or a predefined goal is met. The underlying algorithms are based on artificial intelligence (AI) and learn from historical trends and patterns of the data set. This way, any inconsistency – especially in data sets with high seasonality – can be identified with high accuracy.

 

datapine’s alerts, be it more basic threshold-alerts or advanced neural network alerts that are based on pattern and anomalies recognition, help you to stay in full control of your business key success factors and let you know as soon as something important or unexpected is happening.

 

This chapter describes how to create and manage alerts in datapine. We will introduce you to our different alert types, teach you how to setup alarms by using the different algorithms and explain under which conditions an alarm is thrown. Let’s take a closer look at the different areas of our innovative alert system.

 

 

1) Work with alerts

 

When creating alerts in datapine there is a set of prerequisites that your data needs to fulfill to be able to apply our alert algorithms. To save a chart as an alert your data set should consist of at least two fields: the value you wish to track and a time (or time interval). For instance, you may track your ‘Visitors by hours’ or ‘Sales Revenue by Weeks’. The input format of the date or time field for the alert can thereby be either hourly, daily, weekly or monthly. If you choose an input format larger than the date or time format of your data set, we will automatically sum up the value you wish to track by the selected input format. For example, if you track your Website Visitors by minutes, the smallest input format for alerts is hours, so we will sum up the website visitors by hours. Same applies if you have daily data but wish to use a weekly or monthly input format.

 

To ensure a high accuracy of your alarms when using our neural networks or pattern recognition algorithms, your data set should also have the following attributes:

 

a) For hourly alarms your dataset should consist of at least 1000 data points (Neural Networks) or 500 data points (Pattern Recognition).

 

b) For daily alarms, your data set should consist of approximately 125 data points.

 

c) Alarms using pattern recognition should only be applied to data with a strong pattern or seasonality.

 

2) Alert Types

 

A great way to stay up to date on your business performance is to use datapine’s automated alerts. Our alert function will notify you in case we detect some unexpected developments in your data whether it is based on an algorithmically derived forecast or on your own defined thresholds. This will help you to focus on the metrics that are most important to your business and that demand your immediate attention.

 

datapine’s alerts can be setup using different algorithms such as neural networks, pattern recognition or simply by defining thresholds to get notified as soon as a certain target is reached. Have a look at our alert types to explore the different alarms we offer and what you should keep in mind when setting up alerts using our machine learning algorithms.

 

 

3) Assign Recipient

 

After setting up alerts that will let you know any unexpected event via email, you can customize the sending list of these alerts, adding or removing recipients. This section will show you how. Don’t forget: anyone you want to add as recipient has to be a user in your account beforehand.