Predictor Feature Job Development Task
A Predictor Feature Job Development Task is an data transformation job development task that requires the creation of a feature generation job (which populates a predictor features from a learning record).
- AKA: Featurization, Feature Space Construction.
- Context:
- It can (typically) be preceded by a Feature Space Design Task.
- It can range from being a Low-Level Feature Creation Task to being a High-Level Feature Creation Task.
- It can be solved by a Featurization System (that implements a featurization algorithm).
- It can be supported by a Feature Vector Hashing Task.'
- It can be finalized by a Feature Selection Task.
- It can range from being a Text Featurization Task, a Timeseries Featurization Task, ...
- Example(s):
- the one needed to deliver organization X's item recommendation system.
- …
- Counter-Example(s):
- See: Labeling System, Data Processing.
References
2014
- (Wikipedia, 2014) ⇒ http://en.wikipedia.org/wiki/feature_vector Retrieved:2014-8-10.
- … The vector space associated with these vectors is often called the feature space. In order to reduce the dimensionality of the feature space, a number of dimensionality reduction techniques can be employed.
Higher-level features can be obtained from already available features and added to the feature vector, for example for the study of diseases the feature 'Age' is useful and is defined as Age = 'Year of death' - 'Year of birth' . This process is referred to as feature construction.[1] [2] Feature construction is the application of a set of constructive operators to a set of existing features resulting in construction of new features. Examples of such constructive operators include checking for the equality conditions {=, ≠}, the arithmetic operators {+,−,×, /}, the array operators {max(S), min(S), average(S)} as well as other more sophisticated operators, for example count(S,C)[3] that counts the number of features in the feature vector S satisfying some condition C or, for example, distances to other recognition classes generalized by some accepting device. Feature construction has long been considered a powerful tool for increasing both accuracy and understanding of structure, particularly in high-dimensional problems.[4] Applications include studies of disease and emotion recognition from speech.[5]
- … The vector space associated with these vectors is often called the feature space. In order to reduce the dimensionality of the feature space, a number of dimensionality reduction techniques can be employed.
- ↑ Liu, H., Motoda H. (1998) Feature Selection for Knowledge Discovery and Data Mining., Kluwer Academic Publishers. Norwell, MA, USA. 1998.
- ↑ Piramuthu, S., Sikora R. T. Iterative feature construction for improving inductive learning algorithms. In Journal of Expert Systems with Applications. Vol. 36 , Iss. 2 (March 2009), pp. 3401-3406, 2009
- ↑ Bloedorn, E., Michalski, R. Data-driven constructive induction: a methodology and its applications. IEEE Intelligent Systems, Special issue on Feature Transformation and Subset Selection, pp. 30-37, March/April, 1998
- ↑ Breiman, L. Friedman, T., Olshen, R., Stone, C. (1984) Classification and regression trees, Wadsworth
- ↑ Sidorova, J., Badia T. Syntactic learning for ESEDA.1, tool for enhanced speech emotion detection and analysis. Internet Technology and Secured Transactions Conference 2009 (ICITST-2009), London, November 9–12. IEEE
2006
- (Bishop, 2006) ⇒ Christopher M. Bishop. (2006). “Pattern Recognition and Machine Learning." Springer. ISBN:0387310738
- QUOTE: … This pre-processing stage is sometimes also called feature extraction. Note that new test data must be pre-processed using the same steps as the training data. ...