# Time Series MOC
### Concepts
1. [Stationarity](Stationarity.md)
2. [Zillow failure](Zillow-failure.md)
3. [Autocorrelation](Autocorrelation.md)
### In practice
Defining the model to predict the _difference_ in values between time steps rather than the value itself, is a much stronger test of the models predictive powers. In that case, it cannot simply use that the data has a strong autocorrelation, and use the value at time $t$ as the prediction for $t+1$. Due to this, it provides a better test of the model and if it has learnt anything useful from the training phase, and whether analyzing historical data can actually help the model predict future changes.
### Dynamics
Time series involve understanding the **dynamics** of a system: its periodic cycles, how it trends over time, its regular regime and its sudden spikes. Note how this differs from standard ML ([Machine Learning vs Time Series](Machine%20Learning%20vs%20Time%20Series.md)).
---
Date: 20211231
Links to:
Tags:
References:
* [Time Series ML Problems](https://towardsdatascience.com/how-not-to-use-machine-learning-for-time-series-forecasting-avoiding-the-pitfalls-19f9d7adf424)
* [Time Series in ML, part 2](https://www.linkedin.com/pulse/how-use-machine-learning-time-series-forecasting-vegard-flovik-phd-1f/)