Loading...
Please wait, while we are loading the content...
Similar Documents
Validating and tuning
| Content Provider | Scilit |
|---|---|
| Author | Coqueret, Guillaume Guida, Tony |
| Copyright Year | 2020 |
| Description | As is shown in Chapters 5 to 11, ML models require user-specified choices before they can be trained. These choices encompass parameter values (learning rate, penalization intensity, etc.) or architectural choices (e.g., the structure of a network). Alternative designs in ML engines can lead to different predictions, hence selecting a good one can be critical. We refer to the work of Probst et al. (2018) for a study on the impact of hyperparameter tuning on model performance. For some models (neural networks and boosted trees), the number of degrees of freedom is so large that finding the right parameters can become complicated and challenging. This chapter addresses these issues but the reader must be aware that there is no shortcut to building good models. Crafting an effective model is time-consuming and often the result of many iterations. Book Name: Machine Learning for Factor Investing |
| Related Links | https://content.taylorfrancis.com/books/download?dac=C2019-0-11387-8&isbn=9781003034858&doi=10.1201/9781003034858-13&format=pdf |
| Ending Page | 164 |
| Page Count | 20 |
| Starting Page | 145 |
| DOI | 10.1201/9781003034858-13 |
| Language | English |
| Publisher | Informa UK Limited |
| Publisher Date | 2020-08-05 |
| Access Restriction | Open |
| Subject Keyword | Book Name: Machine Learning for Factor Investing Hardware and Architecturee Architectural |
| Content Type | Text |
| Resource Type | Chapter |
