FAQs

Predict: Signals is an AI engine that flags potential anomalies in your financial data. It is an assistant that gut-checks your data to find anomalies resulting from typos, formula-based errors, and misguided assumptions.

Predict: Signals trains on your historical actuals data and learns about your business trends, data seasonalities, and other statistical properties. It then uses this information to formulate a dynamic normal range. Data that falls outside of that range is flagged as anomalies.

Predict works as an intelligent assistant for planning and analysis, helping you save time and improve efficiency and accuracy using AI and your actual data.

Predict: Signals requires at least three years of historical actuals for the AI engine to learn from your data.

Yes, your data is safe. Predict uses on-tenant training and does not rely on third-party services, ensuring your data does not leave your tenant.

Predict is built as a black-box AI engine for enhanced accuracy. It uses multiple algorithms, simulations, and mathematical models, combining their outputs to generate results.

Yes. Predict: Signals is available in both reports (to detect potential anomalies) and templates (to prevent errors). It analyzes past months for actuals-based signals and future months for budget, forecast, and planned scenario signals.

Data points flagged by Predict: Signals are categorized as low, medium, or high risk depending on how far they deviate from the normal range. Risk levels are determined by the AI engine based on your data.

Yes. Right-click any signaled cell or set of cells to resolve them. Once resolved, anomaly flags for those GL values are cleared across Planful.

No, but you can review resolved signals in the Comments section. If needed, you can edit the value to trigger a new signal.

Predict: Projections helps create data-driven planning baselines using AI/ML. It analyzes historical actuals within Planful to understand trends, seasonality, and statistical patterns, generating future projections with proprietary algorithms.

Predict: Projections enables business users to quickly build realistic forecasts and budget scenarios using AI-driven financial forecasting based on historical financial data.

Right-click the line(s) you want to forecast. You can create a full AI scenario using Predict: Projections or apply it within templates.

Forecast accuracy depends on the individual GLs or groups of GLs analyzed. Planful’s domain expertise is built into Predict to enhance reliability and accuracy.

Not currently, but future updates will allow users to choose from a list of supported algorithms for templates using Predict: Projections.

Model training typically takes 8–10 minutes, depending on data volume. When Predict is first enabled, training should be performed manually, then it runs automatically on a quarterly basis.

Navigate to a template containing Accounts Receivable (or any other account) and use the Fill All Lines or Fill Selected Line option to generate projections.