So far you explored the first steps of the basic steps for forecasting , that is ,’Define the Problem’. In this segment, you will explore the next step that is ‘Collecting the Data’. It is very important because all your forecast is dependent on the data. There are some important characteristics that time series data must follow. Let’s understand them from Chiranjoy.
There are three important characteristics that every time series data must exhibit in order for us to make a good forecast.
- Relevant: The time-series data should be relevant for the set objective that we want to achieve.
- Accurate: The data should be accurate in terms of capturing the timestamps and capturing the observation correctly.
- Long enough: The data should be long enough to forecast. This is because it is important to identify all the patterns in the past and forecast which patterns repeat in the future.
You also saw the various types of data sources to get a time-series data. These were:
- Private enterprise data: E.g. financial information about the quarterly results of any private organisation.
- Public data: E.g. government publishes the economic indicators such as GDP, consumer price index etc.
- System/Sensor data: E.g. Logs generated by the servers during their 24/7 working hours.