Corpus ID: 232380379

Domain Specific Concept Drift Detectors for Predicting Financial Time Series

  title={Domain Specific Concept Drift Detectors for Predicting Financial Time Series},
  author={Filippo Neri},
  • F. Neri
  • Published 2021
  • Computer Science, Economics
  • ArXiv
Concept drift detectors allow learning systems to maintain good accuracy on non-stationary data streams. Financial time series are an instance of non-stationary data streams whose concept drifts (market phases) are so important to affect investment decisions worldwide. This paper studies how concept drift detectors behave when applied to financial time series. General results are: a) concept drift detectors usually improve runtime over continuous learning, b) their computational cost is usually… Expand
2 Citations

Figures from this paper

How to Identify Investor's types in real financial markets by means of agent based simulation
  • F. Neri
  • Computer Science, Economics
  • 2021 6th International Conference on Machine Learning Technologies
  • 2021
The paper proposes a computational adaptation of the principles underlying principal component analysis with agent based simulation in order to produce a novel modeling methodology for financial time series and financial markets to find a reduced set of investor’s models (agents) which is able to approximate or explain a targetFinancial time series. Expand
Mapping Learning Algorithms on Data, a useful step for optimizing performances and their comparison
A novel methodology to map learning algorithms on data (performance map) in order to gain more insights in the distribution of their performances across their parameter space is proposed. Expand


Learning with Drift Detection
A method for detection of changes in the probability distribution of examples, to control the online error-rate of the algorithm and to observe that the method is independent of the learning algorithm. Expand
Connectionist Learning Procedures
These relatively simple, gradient-descent learning procedures work well for small tasks and the new challenge is to find ways of improving their convergence rate and their generalization abilities so that they can be applied to larger, more realistic tasks. Expand
Combining Machine Learning and Agent Based Modeling for Gold Price Prediction
A computational approach combining machine learning (simulated annealing) and agent based simulation is shown to approximate financial time series and the methodology can be applied under several meta-learning conditions and its experimentation on the real world SPDR Gold Trust (GLD) timeseries. Expand
Classical Linear Regression
Learning from Time-Changing Data with Adaptive Windowing
A new approach for dealing with distribution change and concept drift when learning from data sequences that may vary with time is presented, using sliding windows whose size is recomputed online according to the rate of change observed from the data in the window itself. Expand
Early Drift Detection Method
A method for detecting concept drift, even in the case of slow gradual change, based on the estimated distribution of the distances between classiflcation errors that can be used with any learning algorithm in two ways: using it as a wrapper of a batch learning algorithm or implementing it inside an incremental and online algorithm. Expand
Simulating and modelling the DAX index and the USO Etf financial time series by using a simple agent-based learning architecture
Reactive Soft Prototype Computing for Concept Drift Streams
This work proposes a concept drift detection strategy followed by a prototype-based adaptation strategy that provides stable and quick adjustments in times of change in the real-time information system. Expand
Combining machine learning and agent based modeling for gold price prediction. Artificial life and Evolutionary Computation
  • Communications in Computer and Information Science
  • 2019