Time Series

Predict sales behavior in the coming months. This is an application of Time Series. In essence, the technique relies on a date column and a metric, to analyze three factors:

1. Seasonality: peaks at certain cyclical moments (e.g. Christmas).

2. Trend: analyzes the speed of growth, decline or stagnation.

3. Amplitude: if there are rises and falls over time, it measures whether the distances between peaks and valleys have intensified or not.

Gaio can project the next months or days. Gaio uses the Facebook algorithm, Prophet, to perform calculations.

Various techniques and parameterizations are applied to the data, generating several projections and their errors are calculated. The model with the lowest error is chosen and the projections are saved in a table in Gaio.

1. Settings

To make projections, click the table that contains a date column and the metric you want to project. Under Tasks, click Time Series.

1. Define the name of the table to be generated with the projections.

2. Select the column that has the date that will be used for modeling and your sequence will be projected.

3. Measure : a numeric column must be entered in this location so that it can be projected. If the table is not aggregated, Gaio will add the values in this column automatically.

4. Frequency : you can choose whether projections are made daily or monthly.

5. Classification : This field is optional. If any column is entered, Gaio will build a series for each value. Example: salesperson. Gaio will calculate as many series as there are salespeople in the company.

6. Period : define how many periods (days or months) you want to be projected.

2. Results

The result of executing the Time Series brings a set of columns according to the image below:

1. category : if a column has not been defined in the Classification item in the table configuration, this column will have the value nd in all rows. If you have defined, for example , State as the Classification column , for each State there will be a large set of rows in this generated table. For States with less than two lines, no series will be generated.

2. dt : column of dates in the historical table that also has future dates for projections.

3. real : historical values of the column chosen as Measure in Configuration.

4. type : receives the actual and forecast values , to separate the historical period from the projection period.

5. forecast: This column has values for all lines, historical and forecast . This is because the model makes projections for the entire past, where it can calculate how far from reality the projections are.

6. lower : lower limit of projections.

7. upper : upper limit of the projections.

3. Visualization

It is generally desired to present the series and its projection graphically. In the Report task, there is an exclusive graph for Time Series .

To create a chart when only one series was projected (without a column in the Classification ), go to Reports, drag all the fields except the category and sort in ascending order by the dt column , the date. Then choose the graphic in the image below:

The result should be something similar to the graph below. The blue balls are the actual historical results. The green line is the model, which is applied to the past and future, generating projections.