Using a variety of R time series analysis techniques, I investigated the daily bike rental demand data-set during this project. Based on our analysis, it appears that the data has significant seasonal and trend components, which ARIMA model was able to decompose and model. Task 1: Open and Examine the Data After the hourly and daily data were successfully loaded and examined, a clear seasonal pattern was found in the data. Task 2: Create Interactive Time Series Plots: To better understand the structure of the data, interactive plots were made to visualize the hourly and daily data. Task 3: Smooth Time Series Data: The underlying trend was highlighted in the daily data by using the moving average smoothing technique. Task 4: Decompose and assess Time Series Data Stationarity: Once the seasonal, trend, and residual components of the data were separated out, the ADF test showed that the data was not stationary. The data became stationary after differencing and log transformation were applied. Task Five: Using ARIMA Models to Fit and Forecast Time Series Data: After being developed and assessed, an ARIMA model was found to fit the data well.