Online ARIMA Algorithms for Time Series Prediction

نویسندگان

  • Chenghao Liu
  • Steven C. H. Hoi
  • Peilin Zhao
  • Jianling Sun
چکیده

Autoregressive integrated moving average (ARIMA) is one of the most popular linear models for time series forecasting due to its nice statistical properties and great flexibility. However, its parameters are estimated in a batch manner and its noise terms are often assumed to be strictly bounded, which restricts its applications and makes it inefficient for handling large-scale real data. In this paper, we propose online learning algorithms for estimating ARIMA models under relaxed assumptions on the noise terms, which is suitable to a wider range of applications and enjoys high computational efficiency. The idea of our ARIMA method is to reformulate the ARIMA model into a task of full information online optimization (without random noise terms). As a consequence, we can online estimation of the parameters in an efficient and scalable way. Furthermore, we analyze regret bounds of the proposed algorithms, which guarantee that our online ARIMA model is provably as good as the best ARIMA model in hindsight. Finally, our encouraging experimental results further validate the effectiveness and robustness of our method.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Modeling and prediction of time-series of monthly copper prices

One of the main tasks to analyze and design a mining system is predicting the behavior exhibited by prices in the future. In this paper, the applications of different prediction methods are evaluated in econometrics and financial management fields, such as ARIMA, TGARCH, and stochastic differential equations, for the time-series of monthly copper prices. Moreover, the performance of these metho...

متن کامل

Prediction of global sea cucumber capture production based on the exponential smoothing and ARIMA models

Sea cucumber catch has followed “boom-and-bust” patterns over the period of 60 years from 1950-2010, and sea cucumber fisheries have had important ecological, economic and societal roles. However, sea cucumber fisheries have not been explored systematically, especially in terms of catch change trends. Sea cucumbers are relatively sedentary species. An attempt was made to explore whether the tim...

متن کامل

Prediction of the Type and Amount of Surface Water Pollutants using Time Series Models (ARIMA) and L-THIA Model (Case Study: Namrood Sub-Basin, Hablehrood Watershed)

     Due to the important role of non-point source pollution in water resources management, in this study time series modeling was applied to forecast water quality parameters and L-THIA model (one type of non-point source pollution models) was applied to estimate water pollutants. The purpose of this study was to compare results of L-THIA model and ARIMA models in Namrood sub-basin located in ...

متن کامل

Time Series Models to Predict the Monthly and Annual Consumption of Natural Gas in Iran

Considering the fact that natural gas is a widely used energy source,  the prediction of its consumption can be useful (Derek LAM, 2013). As Iran has one of the largest gas reserves in the world, its consumption in the country can affect the worldwide price of gas, Therefore, the current research is useful both from economic and environmental point of view. ...

متن کامل

Time Series Models to Predict the Monthly and Annual Consumption of Natural Gas in Iran

Considering the fact that natural gas is a widely used energy source,  the prediction of its consumption can be useful (Derek LAM, 2013). As Iran has one of the largest gas reserves in the world, its consumption in the country can affect the worldwide price of gas, Therefore, the current research is useful both from economic and environmental point of view. ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2016