|A -- USA Stock|| |
USD 62.72 1.75 2.71%
Investors can use this prediction interface to forecast Agilent Technologies historic prices and determine the direction of Agilent Technologies future trends based on various well-known forecasting models. However looking at historical price movement exclusively is usually misleading. Macroaxis recommends to always use this module together with analysis of Agilent Technologies historical fundamentals such as revenue growth or operating cash flow patterns. Although naive historical forecasting may sometimes provide an important future outlook for the firm we recommend to always cross-verify it against solid analysis of Agilent Technologies systematic risks associated with finding meaningful patterns of Agilent Technologies fundamentals over time. Check also Historical Fundamental Analysis of Agilent Technologies
to cross-verify your projections.
A naive forecasting model for Agilent Technologies is a special case of the moving average forecasting where the number of periods used for smoothing is one. Therefore, the forecast of Agilent Technologies value for a given trading day is simply the observed value for the previous period. Due to the simplistic nature of the naive forecasting model, it can only be used to forecast up to one period.
Given 30 days horizon, the value of Agilent Technologies on the next trading day is expected to be 63.091471
Agilent Technologies Prediction Pattern
Agilent Technologies Forecasted Value
October 23, 2018
Next Trading Day Expected Value
Model Predictive Factors
|AIC||Akaike Information Criteria||37.5569|
|Bias||Arithmetic mean of the errors ||None|
|MAD||Mean absolute deviation||1.0147|
|MAPE||Mean absolute percentage error||0.015|
|SAE||Sum of the absolute errors||17.25|
This model is not at all useful as a medium-long range forecasting tool of Agilent Technologies. This model really is a simplistic model, and is included partly for completeness and partly because of its simplicity. It is unlikely that you'll want to use this model directly. Instead, consider using either the moving average model, or the more general weighted moving average model with a higher (i.e. greater than 1) number of periods, and possibly a different set of weights.