Introduction toXLMiner™The Data mining add-in for Microsoft Excel.TIME SERIESXLMiner and Microsoft Office are registered trademarks of the respective owners.
TIME SERIESTime series analysis is done to understand the distribution of data points over time and such an analysis is useful for the purpose of prediction – for example, the future trends over time can be predicted by information extracted from the past performance. In XLMiner, there are two exploratory techniques used for time series analysisACF (Autocorrelation Function):Autocorrelation is the correlation between observations of a time series separated by say, k time units. Suppose there are n time based observations, in ACF technique XLMiner�finds correlation between the observations for different lags.PACF (Partial Autocorrelation Function):PACF technique is used to compute and plot the partial autocorrelations of a time series. With PACF we can find correlation between some components of the series, eliminating the contribution of other components. PACF technique measures the strength of relationship with other terms being accounted forhttp://dataminingtools.net
TIME SERIES- Partitioning DataIn order to find if the time series created using XLMiner is accurate enough to proceed, we need to partition the data set into training and validation partitions and then see if the time series pattern is same for both. If the difference is too much we need to train our model againhttp://dataminingtools.net
TIME SERIES- ACFhttp://dataminingtools.net
TIME SERIES- Partitioning Datahttp://dataminingtools.net
Thank youFor more presentations, tutorial videos on Data Mining, please visithttp://dataminingtools.nethttp://dataminingtools.net

XL-Miner: Timeseries

  • 1.
    Introduction toXLMiner™The Datamining add-in for Microsoft Excel.TIME SERIESXLMiner and Microsoft Office are registered trademarks of the respective owners.
  • 2.
    TIME SERIESTime seriesanalysis is done to understand the distribution of data points over time and such an analysis is useful for the purpose of prediction – for example, the future trends over time can be predicted by information extracted from the past performance. In XLMiner, there are two exploratory techniques used for time series analysisACF (Autocorrelation Function):Autocorrelation is the correlation between observations of a time series separated by say, k time units. Suppose there are n time based observations, in ACF technique XLMiner�finds correlation between the observations for different lags.PACF (Partial Autocorrelation Function):PACF technique is used to compute and plot the partial autocorrelations of a time series. With PACF we can find correlation between some components of the series, eliminating the contribution of other components. PACF technique measures the strength of relationship with other terms being accounted forhttp://dataminingtools.net
  • 3.
    TIME SERIES- PartitioningDataIn order to find if the time series created using XLMiner is accurate enough to proceed, we need to partition the data set into training and validation partitions and then see if the time series pattern is same for both. If the difference is too much we need to train our model againhttp://dataminingtools.net
  • 4.
  • 5.
    TIME SERIES- PartitioningDatahttp://dataminingtools.net
  • 6.
    Thank youFor morepresentations, tutorial videos on Data Mining, please visithttp://dataminingtools.nethttp://dataminingtools.net