TIM, or the Tangent Information Modeler, is an automatic predictive model building engine that automates the forecasting and anomaly detection process by analyzing time series data and generating accurate models based on the patterns it detects. It builds high quality, explainable models on continuously evolving data in any circumstances, in a fast and accurate way. This empowers users to take informed decisions and improve processes, driving business value from predictive analytics.

TIM empowers users to adapt to new situations by allowing models to be rebuilt or recalibrated continuously. Whereas model recalibration only adjusts the parameters of the model and leaves the structure of the model (features) intact, model rebuilding starts by identifying new features and then builds a completely new model. Through the identification of new features, the process of model rebuilding is made robust to changes in the underlying processes.

An important aspect in achieving high quality results, lies in the ability of TIM to not only take past values of the target variable as input, but also various additional variables that might relate to the target variable. In doing so, TIM is set up to take all possibly explanatory data into account when building models.