Maple Syrup Production Predictor
🎯 BRIEF
The goal of the project was to build a multivariate time series forecaster to predict the production quantity of Maple Syrup for 2021 considering different factors that affect its production—Daily Precipitation, Daily Soil Moisture, Daily Temperature, and Eight Day NDVI (Normalized Difference Vegetation Index). Different metrics were used to assess the causality and stationarity of different time series and to build the most suitable Vector Auto Regressive model.
🔧 TOOLS
Python, statsmodels, numpy, pandas, seaborn, Matplotlib
🤝 CONTRIBUTION
Built a robust multivariate Vector Autoregressive Model to predict Maple Syrup production, securing 5th place out of 100 participants.
Employed different statistical methods for stationarity check, lag order estimation, and parameter analysis.Â
Optimized and validated the model utilizing multiple metrics—MAPE, ME, AE, RMSE, etc.—to get the best MAPE of 5.5%.
🏆 TAKEAWAYS
Care must be taken to identify the causal relationships and endogeneity as it can lead to biased estimates and inconsistent standard errors.
đź“· SCREENSHOTS
Forecasted Time Series
Individual Feature Time Series