Interpretation of Autocorrelation plot

I am trying to understand better how to read the autocorrelation plot here for a timeseries data.

I ran the following code and got the output as a chart show below.

from pandas.plotting import autocorrelation_plot
autocorrelation_plot(df("y"))


Here y is the dependent variable

Should I derive the following conclusions

• There are no significant autocorrelations.
• The data is random.
• Most of the correlations (except for 2 lags) fall within 95% confidence limits
• This timeseries is not worth forecasting

• There are no significant autocorrelations

The correlation is low (~0.25), but there are significant autocorrelations.

• The data is random & most of the correlations (except for 2 lags) fall within 95% confidence limits

The confidence intervals are used to show which autocorrelations are significant. As you rightly observed, a couple peaks jump out of this region and this tells us that these few correlations are statistically significant, the rest is random. This post may be helpful here.

• This timeseries is not worth forecasting

As per the previous point, there are a couple of statistically significant weak correlations in this dataset. But they are not strong, so a periodicity based forecasting model probably wouldn't be very accurate.

• Thank you. This helped ! – Senthil Feb 27 at 1:02