A well is in natural flow (flowing well) when the pressure at the bottom of it is sufficient to boost its production to the surface. The flowing wells make use of some surface restrictions in order to regulate the flowing rate in such a way that the overall well performance is a function of several variables. Examples of these variables are tubing size, choke size, wellhead pressure, flow line size, and perforation density. This implies that changing any of these variables will alter well performance.One of the techniques for the analysis of the production is studying the wellhead pressure declination, since, in critical flow conditions, flow is a function of wellhead pressure. From wellhead pressure visualization you can identify the behavior of each well and determine the presence of paraffin or other materials affecting its production or, in the worst case, cause suspension of extraction process.The present work performs the analysis of wellhead pressure curves using data science, with the purpose predict pressure curves and the early identification of anomalies that could occur for timely correction.The data in this work correspond to 130 flowing wells from NOC Oil Sur. The study began with a filtering process of the pressure curve, with two specific objectives: first, eliminate atypical values from the time series, and second, smooth the curve in such a way that future predictions can be performed.Next, the ARIMA methodology (Auto-regressive integrated moving average) was applied with the purpose of predicting values of the curve. This is based on the past values of the time series to infer the future values, the trend characteristic of the curve was used to apply this methodology.Then, to identify the anomaly a model was designed based on the declination of the curve. The pressure declination curve is a descending exponential, so the first and second derivatives indicate the trend (ascending - descending) and curvature (concave or convex) of it. Once these values are available, they are classified according to the anomaly: paraffin, encrustation or obstruction.Finally, the model is being tested in the control room in Loma Campana, delivering a probability of occurrence of any of the anomalies named every hour.