Nonparametric sequential prediction of time series

Biau, Gérard; Bleakley, Kevin; Györfi, László; Ottucsák, György

doi:10.1080/10485250802680730

Cited by 20 publications

(19 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Grounded on nonparametric prediction [Györfi and Schäfer 2003], this category consists of several pattern-matching based investment strategies [Györfi et al 2006;Györfi et al 2007;Li et al 2011a]. Moreover, some techniques are also applied to the sequential prediction problem [Biau et al 2010]. Now let us describe the main idea of the Pattern-Matching based approaches [Györfi et al 2006], which consists of two steps, that is, the Sample Selection step and Portfolio Optimization step 1 .…”

Section: Pattern-matching Based Approachesmentioning

confidence: 99%

Online Portfolio Selection

Li¹,

Hoi²

2018

101

View full text Add to dashboard Cite

Online portfolio selection is a fundamental problem in computational finance, which has been extensively studied across several research communities, including finance, statistics, artificial intelligence, machine learning, and data mining, etc. This article aims to provide a comprehensive survey and a structural understanding of published online portfolio selection techniques. From an online machine learning perspective, we first formulate online portfolio selection as a sequential decision problem, and then survey a variety of state-of-the-art approaches, which are grouped into several major categories, including benchmarks, "Follow-the-Winner" approaches, "Follow-the-Loser" approaches, "Pattern-Matching" based approaches, and "Meta-Learning Algorithms". In addition to the problem formulation and related algorithms, we also discuss the relationship of these algorithms with the Capital Growth theory in order to better understand the similarities and differences of their underlying trading ideas. This article aims to provide a timely and comprehensive survey for both machine learning and data mining researchers in academia and quantitative portfolio managers in the financial industry to help them understand the state-of-the-art and facilitate their research and practical applications. We also discuss some open issues and evaluate some emerging new trends for future research directions.

show abstract

Section: Pattern-matching Based Approachesmentioning

confidence: 99%

Online Portfolio Selection

Li¹,

Hoi²

2018

101

View full text Add to dashboard Cite

show abstract

“…average) over these query results [44,18,11,8]. These methods however cannot estimate the analytical predictive uncertainty directly.…”

Section: Time Series Prediction Methodsmentioning

confidence: 99%

SMiLer

Zhou

Tung

2015

Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data

View full text Add to dashboard Cite

It is useful to predict future values in time series data, for example when there are many sensors monitoring environments such as urban space. The Gaussian Process (GP) model is considered as a promising technique for this setting. However, the GP model requires too high a training cost to be tractable for large data. Though approximate methods have been proposed to improve GP's scalability, they usually can only capture global trends in the data and fail to preserve small-scale patterns, resulting in unsatisfactory performance.We propose a new method to apply the GP for sensor time series prediction. Instead of (eagerly) training GPs on entire datasets, we custom-build query-dependent GPs on small fractions of the data for each prediction request.Implementing this idea in practice at scale requires us to overcome two obstacles. On the one hand, a central challenge with such a semi-lazy learning model is the substantial model-building effort at kNN query time, which could lead to unacceptable latency. We propose a novel two-level inverted-like index to support kNN search using the DTW on the GPU, making such "just-in-time" query-dependent model construction feasible for real-time applications.On the other hand, several parameters should be tuned for each time series individually since different sensors have different data generating processes in diverse environments. Manually configuring the parameters is usually not feasible due to the large number of sensors. To address this, we devise an adaptive auto-tuning mechanism to automatically determine and dynamically adjust the parameters for each time series with little human assistance.Our method has the following strong points: (a) it can make prediction in real time without a training phase; (b) it can yield superior prediction accuracy; and (c) it can effectively estimate the analytical predictive uncertainty.To illustrate our points, we present SMiLer, a semi-lazy time series prediction system for sensors. Extensive experiments on real-world datasets demonstrate its effectivePermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. ness and efficiency. In particular, by devising a two-level inverted-like index on the GPU with an enhanced lower bound of the DTW, SMiLer accelerates the efficiency of kNN search by one order of magnitude over its baselines. The prediction accuracy of SMiLer is better than the state-of-the-art competitors (up to 10 competitors) with better estimation of predictive uncertainty.

show abstract

“…• MeanExpertMixture is an online prediction algorithm described in [14]. It is based on conditional mean estimation and close in spirit to the strategy QuantileExpertMixture 0.5 .…”

Section: Methodsmentioning

confidence: 99%

“…Thus, for practical reasons, we chose a finite grid (k, ℓ) ∈ K × L of experts (positive integers), let Next, as indicated by the theoretical results, we fixed η n = 1/n. For a thorough discussion on the best practical choice of η n , we refer to [14]. To avoid numerical instability problems while computing the p k,l,n , we applied if necessary a simple linear transformation on all L n (h (k,l) n ), just to force these quantities to belong to an interval where the effective computation of x → exp(−x) is numerically stable.…”

Section: Algorithmic Settingsmentioning

confidence: 99%

See 1 more Smart Citation

Sequential Quantile Prediction of Time Series

Biau

Patra²

2011

IEEE Trans. Inform. Theory

Self Cite

View full text Add to dashboard Cite

Motivated by a broad range of potential applications, we address the quantile prediction problem of real-valued time series. We present a sequential quantile forecasting model based on the combination of a set of elementary nearest neighbor-type predictors called "experts" and show its consistency under a minimum of conditions. Our approach builds on the methodology developed in recent years for prediction of individual sequences and exploits the quantile structure as a minimizer of the so-called pinball loss function. We perform an in-depth analysis of real-world data sets and show that this nonparametric strategy generally outperforms standard quantile prediction methods.

show abstract

Nonparametric sequential prediction of time series

Cited by 20 publications

References 27 publications

Online Portfolio Selection

Online Portfolio Selection

SMiLer

Sequential Quantile Prediction of Time Series

Contact Info

Product

Resources

About