Data mining, sometimes referred to as knowledge discovery, is the process of filtering large volumes of data in search of correlations, patterns, and trends. A linear pattern is a continuous decrease or increase in numbers over time. In a graph, this data appears as a straight line diagonally inclined up or down (the angle can be steep or shallow). Therefore, the trend can be upward or downward.
If a company wants to get clear and accurate results, it must choose the most appropriate algorithm and technique for a particular type of data and analysis. In this analysis, the line is a curved line that shows the data values that initially rise or fall, and then shows a point at which the trend (increase or decrease) stops rising or falling. Every data set is unique, and it's important to identify trends and patterns in the underlying data. This technique produces nonlinear curved lines in which data goes up or down, not at a constant rate, but at a higher rate.
A basic understanding of the types and uses of trend and pattern analysis is crucial if a company wants to take full advantage of these analytical techniques and produce reports and results that help it achieve its objectives and compete in the market of its choice. In forecasting, the goal is to “model all components according to some trend patterns to the point that the only component that remains unexplained is the random component”. Instead of a straight line pointing diagonally upwards, the chart will show a curved line where the last point of recent years will be higher than that of the first year if the trend is upward.