Anna is our AI-powered virtual analyst and she is very good at descriptive and diagnostic analytics. What does that mean? It means that like a human analyst, Anna is great at summarising historical data to determine what has happened and why.

Anna’s analytic capabilities are focused on three main areas:

  • Trend analysis: identifying patterns in structured and transactional data to help users understand performance over time (see here for more information)

  • Root cause analysis: determine drivers of change by utilising several machine learning techniques such as Cramér's V to highlight the most likely causes for users (see here for more information)

  • Anomaly or outlier detection: proactively surfacing unexpected insights hidden within the data through a range of different algorithms including STL, S-ARIMA and PCA (see here for more information)

How does she do this?

Like any good analyst, Anna will determine and apply the most appropriate statistical technique based on the scenario presented before her to provide actionable insights. For example, to conduct root causes analysis, Anna utilises ensemble learning which combines several machine learning techniques such as Random Forest, Named Entity Recognition (NER) and Cramér's V into one analytical model in order to decrease variance, bias and improve prediction accuracy.

Data Stories:

Not only does Anna use artificial intelligence to automate the insight generation process, she also packages these insights into intuitive stories and charts for users to consume (examples listed below). In order to perform this type of analysis, Anna requires structured and transactional data (more information on data requirements can be found here).

Example data stories:

  1. Large increases/decreases: surfacing largest change and percentage change per category

  2. 80/20 principle: identifying top categories that make up majority of the total

  3. New, lost and returning: calculating new, lost and return categories within the current period

  4. Outliers and anomalies: highlighting unexpected changes within the dataset

Example Chart/ Analytics Types:

  1. Trend analysis

  2. Seasonality deconstruction

  3. Mix indexation analysis

  4. Correlation analysis

  5. Rank analysis

  6. Day of week analysis

If you have any questions, please contact us at

Did this answer your question?