MicroStrategy ONE

Time Series Forecasting Analysis

Time series forecasting analysis is supported in MicroStrategy Cloud environments and starting in MicroStrategy ONE (March 2024), time series forecasting analysis is supported on the MicroStrategy Cloud for Government platform. You can only use this feature in MicroStrategy Library (web browser only) and Workstation when you connect to a Library server.

MicroStrategy ONE Update 11 introduces time series forecasting. Time series forecasting is a powerful technique that empowers businesses to predict future trends and outcomes based on historical data patterns. At its core, it involves analyzing data points collected over successive intervals of time to identify underlying patterns, trends, and fluctuations. This predictive approach is particularly valuable in anticipating future changes and making informed decisions. By harnessing the power of advanced machine learning algorithms, MicroStrategy's time series forecasting provides users with a seamless and intuitive means to uncover insights hidden within their data. Whether you're a business analyst, marketing manager, or finance executive, this capability offers a gateway to proactively strategize, allocate resources efficiently, and capitalize on opportunities. The integration of forecasting analysis saves valuable time and effort for users who previously relied on manual data processing and complex analytics methods to predict future outcomes.

Access Time Series Forecasting

Time series forecasting is part of the MicroStrategy AI add-on bundle and is available for MicroStrategy Cloud Environment (MCE) customers starting in MicroStrategy ONE Update 11 (September 2023). Only users and user groups with the Use Auto Assistant and ML Visualizations privilege can access the Forecast Line Chart.

Forecasting analysis is available in the following ways:

  • Through the visualization gallery in a dashboard, using a drag and drop interface to create a Forecast Line Chart visualization.

  • Auto can utilize natural language queries to perform forecasting analysis.

Create a Forecast Analysis Line Chart

  1. Open a dashboard for editing.

  2. In the top toolbar, click Visualization .

  3. Choose Insight+ > Forecast Line Chart .

  4. Drag a metric and time attribute from the Datasets panel to the Editor panel.

  5. View the rendered visualization with the forecasted values on the right.

  6. The default number of forecasted points is five. To change this number, go to Format panel and click Visualization Options . In Forecast length, change the number of forecasted points. The maximum number of forecasted points is 100.

Customize the Appearance of Forecast Line Charts

Make your forecasts visually engaging by customizing the appearance of your Forecast Line Chart. Adjust colors, fonts, and labels to match your preferences and create a chart that's not only insightful, but looks great!

By default, the forecasted area of the line chart uses the first color from the chosen color palette. However, you can customize the color, data labels, markers, and divider line using the Format panel.

Customize Forecast Lines, Confidence Bands, Dividing Lines, and Forecast Line Markers

  1. In the Format panel, click Text and Form .

  2. Select Forecast from the drop down.

  3. Select options to format the Forecast Lines, Confidence Band, Dividing Line, as well as enable and color markers on the forecast line.

Customize Line Color and Style

  1. In the Format panel, click Text and Form .

  2. Select Data Labels and Shapes from the drop down.

  3. Under Shape, select a Line style and color.

Customize Data Labels

  1. In the Format panel, click Visualization Options .

  2. Enable Data Labels to view them.

  3. By default, only the labels that don’t overlap are visible. Deselect Hide overlapping labels to enable all data labels.

  4. In the Format panel, click Text and Form

  5. Under Font, use the text formatting options to change data label font and color options.

Customize Line Markers

  1. In the Format panel, click Text and Form

  2. Select Data Labels and Shapes from the drop down.

  3. Under Shape, enable Show marker to enable all markers on a line.

  4. If markers are enabled, select the Marker Color.

Use Auto Answers for Forecasting

To leverage the power of predictive insights within Auto, enter your forecasting question using natural language. For example, "What's the projected sales for the next quarter?" Auto Answers provides you with accurate forecasts based on your query, its deep understanding of your dataset objects, and advanced machine learning algorithms.

Auto's response consists of a clear natural language description of the forecasted data with an accompanying forecast line chart visualization, making it easy to understand what lies ahead. While the visualization may contain a limited number of data points when rendered in the confined space of the chat panel, expanding the prompt’s response displays the entire set of existing and forecasted data points.

Here's how you can delve into predictions using Auto Answers. Auto Answers is presented in expanded mode in the examples below:

  • Next Few Months Prediction Start with a given monthly sales dataset. You can ask Auto Answers to forecast the sales for the next few months. The algorithm adeptly handles the task even if you're requesting predictions for an entire year based on monthly data.

  • Forecast at a higher level against lower level data Start with a given monthly sales dataset. You can ask Auto Answers to forecast the sales for the next year based on monthly data.

  • Hyper-parameters Tuning For those who want more control, there's an advanced option. You can adjust hyper-parameter values within your question. For instance, if the auto-detected seasonality doesn't yield optimal results, you can specify a seasonality length of your choice or set a specific confidence level. This flexibility extends to using different season and trend models, like toggling between multiplicative and additive models.

  • Applying Filters Predictions can also be filtered. The example below demonstrates forecasting for the next three months, considering a specific category such as music. Keep in mind that the month attribute is represented as an integer, not a time-based value.

Tips and Best Practices

Tips for Effective Forecasting Questions

  • Be Specific Instead of asking broad questions like "How will our sales perform?", ask about a specific time frame or metric. For example, "What's the projected sales for the next quarter?".

  • Use Natural Language Auto understands conversational language. Frame your questions in a natural way, as if you were asking a colleague.

  • Include Relevant Attributes Include the necessary attributes and metrics in your question to ensure Auto understands the context.

  • Leverage the auto-complete feature For optimal forecasting using Auto, it's recommended to choose metrics and attributes from the auto-complete suggestions. This ensures precise understanding by Auto for accurate forecasting.

  • Avoid Ambiguity Keep your questions clear and unambiguous. Complex or convoluted queries might lead to inaccurate responses.

  • While MicroStrategy enables forecasting of higher-level time units against lower-level data using Auto (such as forecasting next year's cost based on monthly attributes), there are key considerations:

    • Limit on 100 Forecast Points When requesting a forecast of a higher-level time unit against lower-level data, be aware of the 100-point forecast limit. For instance, if your dashboard data is at the daily level and you request a forecast for the next year, the forecast would encompass 1 year's worth of daily data points, exceeding the 100-point limit.

    • Forecast Failure for Incompatible Levels Asking for a forecast of lower-level data against higher-level data results in a forecast failure. For instance, if your dashboard data is at the monthly level and you ask for a forecast for the next week's or next day's values, it won't be feasible due to the data level discrepancy.

Best Practices When Using the Forecasting Analysis Feature

  • Ensure Sufficient Data Volume for Accurate Forecasting

    For more accurate forecasting results, it's important to ensure that your data volume is substantial enough. Behind the scenes, MicroStrategy automatically detects the seasonality of your data. To achieve optimal forecasting outcomes, we recommend that the data you intend to forecast should have at least two complete seasons of historical data.

  • Use High-Quality Continuous Time-Based Data for Forecasting

    While MicroStrategy performs lightweight data processing before forecasting, such as eliminating duplicated data and filling in some missing metric data, it's advisable to conduct forecasting on continuous, high-quality, time-based data. Forecasting results can be compromised if there's a significant amount of missing metric data. It's important to note that forecasts may fail or yield suboptimal outcomes if attributes contain NULL or NaN (Not-a-Number) values.

Optimize Forecast Line Chart Interpretation

Get the most out of your forecast line chart visualization!

  • Hover for Insights Hover your cursor over data points on the forecast line chart to reveal tooltips. These tooltips provide detailed information about forecasted values, as well as upper and lower bounds.

  • Info icon Hover over the info icon to see information about the underlying model and its parameters.

  • Expand for Clarity If you need more detailed information and the ability to display the entire set of data points, expand the visualization. This enhances the readability of the chart.

Understand Forecasting Limitations

The limitations addressed below are associated with the MicroStrategy ONE Update 11 release. MicroStrategy is actively working on enhancing this feature, and some of these limitations may be addressed in upcoming versions. For the latest information and updates, we encourage you to visit this page periodically. By understanding and considering these limitations, you can make the most of the forecasting feature and achieve meaningful insights.

  • Attribute and Metric Requirements For accurate predictions, make sure to use exactly one attribute and one metric in your questions to Auto. Queries not meeting this requirement may not yield optimal forecasts.

  • Consider Attribute Forms The attribute used for forecasting should have at least one form with a type of date, datetime, or integer. Timestamp data is not supported.

  • Timezone-based Attributes Forecasting with timezone-based smart attributes is not currently supported.

  • Consolidation and Grouping Forecasting against consolidated or grouped attribute elements is not possible at this time.

  • Granularity Level Forecasts are not available for less than daily level data (such as hourly, minute, or second intervals).

  • Integer-based Forecasting Be cautious when using integer-based time representations in your queries (such as 202101 for January 2021). MicroStrategy does not automatically convert these time representations to date/time format, leading to unexpected results such as 202113 or 202114.

  • Maximum Forecasting Points You can forecast up to 100 future data points. This limit helps ensure efficiency and accurate predictions.

  • Hindcasting and Tuning Currently, hindcasting against existing data is not supported. Additionally, adjusting algorithm hyper-parameters can only be done via Auto in the current release. For example, you can tune the confidence interval by asking Auto to forecast with a specific confidence level, but this is not available in the dashboard authoring interface yet.

Forecast Analysis - FAQs

What time series forecast method is used in the current release?

The time series forecast method used in our current release is called exponential smoothing. This method supports various non-damped models described on the OTexts site. You can refer to the statsmodel Python module (statsmodels.tsa.exponential_smoothing.ets.ETSModel - statsmodels 0.14.0) for more technical details.

What are the default hyper-parameters used for forecasting?

If not specified by the user, the following default hyper-parameters are used:

  • h value Five data points forward

  • Season model additive (adjustable via Auto)

  • Trend model additive (adjustable via Auto)

  • Seasonality length auto (adjustable via Auto)

  • Confidence interval 95% (adjustable via Auto)

The values for the season and trend models can be set to none, multiplicative, or additive via Auto. You can forecast the next three months of sales with a multiplicative trend model.

Can hyper-parameters be adjusted for forecasting?

Yes, you can adjust hyper-parameters for forecasting through Auto. While these hyper-parameters are not exposed in the Format panel in dashboard authoring, you can fine-tune them using Auto.

What types of attributes and metrics are required for successful forecasting?

To successfully forecast data, you need either:

  • Single attribute of a date or datetime type, plus a single metric of interest (recommended)

  • Single attribute of an integer type, plus a metric of interest (when the date/datetime attribute is unavailable for time series forecasting)

Is missing data handled in forecasting?

Yes, the algorithm can automatically fill in missing data if missing data is less than or equal to 90% of the overall data.

What time-based attribute forecasting levels are supported?

Time-based attribute forecasting is supported for the following levels of data: Daily, Weekly, Monthly, Quarterly, and Yearly.

How does integer forecasting work?

For integer forecasting, the algorithm generates the next integer in the sequence. If an integer is used to represent time (such as 202101, 202102), it is not converted to date/time format, and the forecast adds consecutive integers as future points.