Logi Predict 3.0 Tackles Time Series Forecasting with Prophet Algorithm

Logi Predict 3.0 Tackles Time Series Forecasting with Prophet Algorithm

Source: Facebook Research

Logi Analytics has announced the release of Logi Predict 3.0, a new embedded analytics solution that uses the Prophet algorithm. Prophet is a procedure for forecasting time series data based on an additive model where non-linear trends are fit with seasonality. Logi Predict 3.0 was designed to be embedded inside critical applications so application teams can enable users with predictive analytics. The new release comes on the heels of the company’s acquisition of Jinfonet Software earlier this year.

Logi Analytics offers a development platform that allows teams to build, deploy, and maintain the analytics in their applications. With the Logi Platform, analytics content and capabilities are embedded and integrated within an existing application or portal. Application teams maintain control to customize the user experience and meet unique requirements. The add-on Logi Self-Service Module allows users to discover insights and author content from inside your application as well.

The product features a number of capabilities for doing smart data transformations, including thew ability to create a good picture of what’s in a data column. Users can also control how to handle outliers, missing values, and creating statistical bins of quantiles. Logi Predict 3.0 offers granular control and visual column stats with actions as well.

The provider is making it easier to handle high-cardinality columns such as states, suppliers, zip codes, and partners. When users build predictive models, the software automatically takes care of high cardinality columns, without the need for users to transform them.

In a statement to Solutions Review, the company’s Senior Director of Predictive Analytics Sriram Parthasarathy told us: “Predictive, seasonally-adjusted insights are incredibly valuable, but building time series forecasting is complicated. In Logi Predict 3.0, developers can quickly create models to answer questions about sales forecasts, call center call volumes, number of walk-in customers, etc, and embed these within the applications for end-users to take critical actions.”

We encourage you to read Logi’s release notes regarding all the new features in Logi Predict 3.0.

Timothy King
Follow Tim