Forecasting Yearling Prices: A Comparison Of Alternative Time Series Models

The thoroughbred breeding industry in North America has fallen on hard times. The health of this industry is often gauged by prices obtained for yearlings at North American auctions, particularly the average prices of summer sales at Keeneland and Saratoga. We examine various exponential smoothing algorithms along with a market-based structural model, as well as an ARIMA model in generating one-step ahead forecasts. The market-based structural model outperforms the other approaches with respect to both in- and out-of-sample forecasting accuracy.

Download Full-text

Forecasting COVID-19 in Pakistan

PLoS ONE ◽

10.1371/journal.pone.0242762 ◽

2020 ◽

Vol 15 (11) ◽

pp. e0242762

Author(s):

Muhammad Ali ◽

Dost Muhammad Khan ◽

Muhammad Aamir ◽

Umair Khalil ◽

Zardad Khan

Keyword(s):

Time Series ◽

Prediction Interval ◽

Arima Model ◽

The Other ◽

Time Series Models ◽

Cumulative Number ◽

Arima Models ◽

Forecasting Accuracy ◽

Statistical Measures ◽

Better Than

Objectives Forecasting epidemics like COVID-19 is of crucial importance, it will not only help the governments but also, the medical practitioners to know the future trajectory of the spread, which might help them with the best possible treatments, precautionary measures and protections. In this study, the popular autoregressive integrated moving average (ARIMA) will be used to forecast the cumulative number of confirmed, recovered cases, and the number of deaths in Pakistan from COVID-19 spanning June 25, 2020 to July 04, 2020 (10 days ahead forecast). Methods To meet the desire objectives, data for this study have been taken from the Ministry of National Health Service of Pakistan’s website from February 27, 2020 to June 24, 2020. Two different ARIMA models will be used to obtain the next 10 days ahead point and 95% interval forecast of the cumulative confirmed cases, recovered cases, and deaths. Statistical software, RStudio, with “forecast”, “ggplot2”, “tseries”, and “seasonal” packages have been used for data analysis. Results The forecasted cumulative confirmed cases, recovered, and the number of deaths up to July 04, 2020 are 231239 with a 95% prediction interval of (219648, 242832), 111616 with a prediction interval of (101063, 122168), and 5043 with a 95% prediction interval of (4791, 5295) respectively. Statistical measures i.e. root mean square error (RMSE) and mean absolute error (MAE) are used for model accuracy. It is evident from the analysis results that the ARIMA and seasonal ARIMA model is better than the other time series models in terms of forecasting accuracy and hence recommended to be used for forecasting epidemics like COVID-19. Conclusion It is concluded from this study that the forecasting accuracy of ARIMA models in terms of RMSE, and MAE are better than the other time series models, and therefore could be considered a good forecasting tool in forecasting the spread, recoveries, and deaths from the current outbreak of COVID-19. Besides, this study can also help the decision-makers in developing short-term strategies with regards to the current number of disease occurrences until an appropriate medication is developed.

Download Full-text

691. Real-Time Local Influenza Forecasting Using Smartphone-Connected Thermometer Readings

Open Forum Infectious Diseases ◽

10.1093/ofid/ofy210.698 ◽

2018 ◽

Vol 5 (suppl_1) ◽

pp. S249-S249

Author(s):

Aaron Miller ◽

Inder Singh ◽

Sarah Pilewski ◽

Vladimir Petrovic ◽

Philip M Polgreen

Keyword(s):

Time Series ◽

Real Time ◽

Forecast Error ◽

National Level ◽

Model Performance ◽

State Level ◽

Time Series Models ◽

Forecasting Accuracy ◽

Out Of Sample ◽

Influenza Activity

Abstract Background Information regarding influenza activity can inform clinical and public health activities. However, current surveillance approaches induce a delay in influenza activity reports (typically 1–2 weeks). Recently, we used data from smartphone connected thermometers to accurately forecast real-time influenza activity at a national level. Because thermometer readings can be geo-located, we used state-level thermometer data to determine whether these data can improve state-level surveillance estimates. Methods We used temperature readings collected by the Kinsa smart-thermometer and mobile device app to develop state-level forecasting models to predict real-time influenza activity (1–2 weeks in advance of surveillance reports). We used state-reported influenza-like illness (ILI) to represent state influenza activity for 48 US states with sufficient surveillance data. Counts of temperature readings, fever episodes and reported symptoms were computed by week. We developed autoregressive time-series models and evaluated model performance in an adaptive out-of-sample manner. We compared baseline time-series models containing lagged state-reported ILI activity to models incorporating exogenous thermometer readings. Results A total of 10,262,212 temperature readings were recorded from October 30, 2015 to March 29, 2018. In nearly all of the 48 states considered, weekly forecasts of ILI activity improved considerably when thermometer readings were incorporated. On average, state-level forecasting accuracy improved by 23.9% compared with baseline time-series models. In many states, such as PA, New Mexico, MA, Virginia, New York and SC, out-of-sample forecast error was reduced by more than 50% when thermometer data were incorporated. In general, forecasts were most accurate in states with the greatest number of device readings. During the 2017–2018 influenza season, the average improvement in forecast accuracy was 24.4%, and thermometer readings improved forecasting accuracy in 41, out of 48, states. Conclusion Data from smart thermometers accurately track real-time influenza activity at a state level. Local surveillance efforts may be improved by incorporating such information. Such data may also be useful for longer-term local forecasts. Disclosures I. Singh, Kinsa Inc.: Board Member, Employee and Shareholder, equity received and Salary. S. Pilewski, Kinsa Inc.: Employee and Shareholder, equity received and Salary. V. Petrovic, Kinsa Inc.: Employee and Shareholder, equity received and Salary.

Download Full-text

Forecasting of Cotton Production in India using Advanced Time Series Models

Indian Journal of Economics and Development ◽

10.35716/ijed/20106 ◽

2020 ◽

pp. 583-590

Keyword(s):

Time Series ◽

Arima Model ◽

Data Series ◽

Time Series Models ◽

Annual Data ◽

Cotton Production ◽

Out Of Sample ◽

Augmented Dickey Fuller ◽

Logarithmic Series ◽

Best Fit

Reliable and timely estimates of cotton production are important providing useful inputs to policymakers for proper foresighted and informed planning. So an attempt was made to forecast the production of cotton at all India level using a time series model. The annual data on production of cotton for the period 1951-52 to 2018-19 was processed. The data were transformed into logarithmic series to stabilize the variance of the series. The stationarity of the data was checked with the help of the Augmented Dickey-Fuller and Phillips-Perron tests. The results of ADF and PP tests confirmed the cotton production series was non-stationary at level, so stationarity in the data was brought by differencing the data series at a first lag. The pattern present in ACF and PACF and results of SCAN and ESACF provided guideline to select the order of non-seasonal ARIMA model. The best fit ARIMA model (ARIMA: 3 1 1) was selected based on AIC criteria and residual diagnostic. The performance of the model was judged based on the MAPE value. The out of sample forecast of cotton production at all India level was carried out for the period 2019-20 to 2021-22. The forecasted values indicated a slight increase in the production of cotton compared to 2018-19.

Download Full-text

The Impact of Lengths of Time Series on the Accuracy of the ARIMA Forecasting

International Research in Higher Education ◽

10.5430/irhe.v4n3p58 ◽

2019 ◽

Vol 4 (3) ◽

pp. 58

Author(s):

Lu Qin ◽

Kyle Shanks ◽

Glenn Allen Phillips ◽

Daphne Bernard

Keyword(s):

Time Series ◽

Historical Data ◽

Moving Average ◽

Arima Model ◽

Forecasting Accuracy ◽

Autoregressive Integrated Moving Average ◽

Enrollment Forecasting ◽

Moving Average Model ◽

The Impact ◽

Practical Impact

The Autoregressive Integrated Moving Average model (ARIMA) is a popular time-series model used to predict future trends in economics, energy markets, and stock markets. It has not been widely applied to enrollment forecasting in higher education. The accuracy of the ARIMA model heavily relies on the length of time series. Researchers and practitioners often utilize the most recent - to -years of historical data to predict future enrollment; however, the accuracy of enrollment projection under different lengths of time series has never been investigated and compared. A simulation and an empirical study were conducted to thoroughly investigate the accuracy of ARIMA forecasting under four different lengths of time series. When the ARIMA model completely captured the historical changing trajectories, it provided the most accurate predictions of student enrollment with 20-years of historical data and had the lowest forecasting accuracy with the shortest time series. The results of this paper contribute as a reference to studies in the enrollment projection and time-series forecasting. It provides a practical impact on enrollment strategies, budges plans, and financial aid policies at colleges and institutions across countries.

Download Full-text

A COMPARATIVE ANALYSIS OF ALTERNATIVE UNIVARIATE TIME SERIES MODELS IN FORECASTING TURKISH INFLATION

Journal of Business Economics and Management ◽

10.3846/16111699.2011.620135 ◽

2012 ◽

Vol 13 (2) ◽

pp. 275-293 ◽

Cited By ~ 8

Author(s):

A. Nazif Çatık ◽

Mehmet Karaçuka

Keyword(s):

Time Series ◽

Time Series Models ◽

Unobserved Components ◽

Inflation Forecasting ◽

Long Run ◽

Univariate Time Series ◽

Forecasting Performance ◽

Unobserved Components Model ◽

One Step ◽

Conventional Models

This paper analyses inflation forecasting power of artificial neural networks with alternative univariate time series models for Turkey. The forecasting accuracy of the models is compared in terms of both static and dynamic forecasts for the period between 1982:1 and 2009:12. We find that at earlier forecast horizons conventional models, especially ARFIMA and ARIMA, provide better one-step ahead forecasting performance. However, unobserved components model turns out to be the best performer in terms of dynamic forecasts. The superiority of the unobserved components model suggests that inflation in Turkey has time varying pattern and conventional models are not able to track underlying trend of inflation in the long run.

Download Full-text

Forecasting admissions in psychiatric hospitals before and during Covid-19

10.1101/2021.07.16.21260200 ◽

2021 ◽

Author(s):

Jan Wolff ◽

Ansgar Klimke ◽

Michael Marschollek ◽

Tim Kacprowski

Keyword(s):

Machine Learning ◽

Time Series ◽

Hospital Admissions ◽

Model Performance ◽

Psychiatric Hospitals ◽

Time Series Models ◽

Learning Models ◽

One Step ◽

Machine Learning Models ◽

Better Than

Introduction The COVID-19 pandemic has strong effects on most health care systems and individual services providers. Forecasting of admissions can help for the efficient organisation of hospital care. We aimed to forecast the number of admissions to psychiatric hospitals before and during the COVID-19 pandemic and we compared the performance of machine learning models and time series models. This would eventually allow to support timely resource allocation for optimal treatment of patients. Methods We used admission data from 9 psychiatric hospitals in Germany between 2017 and 2020. We compared machine learning models with time series models in weekly, monthly and yearly forecasting before and during the COVID-19 pandemic. Our models were trained and validated with data from the first two years and tested in prospectively sliding time-windows in the last two years. Results A total of 90,686 admissions were analysed. The models explained up to 90% of variance in hospital admissions in 2019 and 75% in 2020 with the effects of the COVID-19 pandemic. The best models substantially outperformed a one-step seasonal naive forecast (seasonal mean absolute scaled error (sMASE) 2019: 0.59, 2020: 0.76). The best model in 2019 was a machine learning model (elastic net, mean absolute error (MAE): 7.25). The best model in 2020 was a time series model (exponential smoothing state space model with Box-Cox transformation, ARMA errors and trend and seasonal components, MAE: 10.44), which adjusted more quickly to the shock effects of the COVID-19 pandemic. Models forecasting admissions one week in advance did not perform better than monthly and yearly models in 2019 but they did in 2020. The most important features for the machine learning models were calendrical variables. Conclusion Model performance did not vary much between different modelling approaches before the COVID-19 pandemic and established forecasts were substantially better than one-step seasonal naive forecasts. However, weekly time series models adjusted quicker to the COVID-19 related shock effects. In practice, different forecast horizons could be used simultaneously to allow both early planning and quick adjustments to external effects.

Download Full-text

Empirical Evaluation of Alternative Time-Series Models for COVID-19 Forecasting in Saudi Arabia

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18168660 ◽

2021 ◽

Vol 18 (16) ◽

pp. 8660

Author(s):

Isra Al-Turaiki ◽

Fahad Almutlaq ◽

Hend Alrasheed ◽

Norah Alballa

Keyword(s):

Time Series ◽

Saudi Arabia ◽

Time Series Data ◽

Arima Model ◽

Empirical Evaluation ◽

Cubic Spline ◽

Exponential Smoothing ◽

Series Data ◽

Time Series Models ◽

Forecasting Models

COVID-19 is a disease-causing coronavirus strain that emerged in December 2019 that led to an ongoing global pandemic. The ability to anticipate the pandemic’s path is critical. This is important in order to determine how to combat and track its spread. COVID-19 data is an example of time-series data where several methods can be applied for forecasting. Although various time-series forecasting models are available, it is difficult to draw broad theoretical conclusions regarding their relative merits. This paper presents an empirical evaluation of several time-series models for forecasting COVID-19 cases, recoveries, and deaths in Saudi Arabia. In particular, seven forecasting models were trained using autoregressive integrated moving average, TBATS, exponential smoothing, cubic spline, simple exponential smoothing Holt, and HoltWinters. The models were built using publicly available daily data of COVID-19 during the period of 24 March 2020 to 5 April 2021 reported in Saudi Arabia. The experimental results indicate that the ARIMA model had a smaller prediction error in forecasting confirmed cases, which is consistent with results reported in the literature, while cubic spline showed better predictions for recoveries and deaths. As more data become available, a fluctuation in the forecasting-accuracy metrics was observed, possibly due to abrupt changes in the data.

Download Full-text

The Comparison between ARIMA and ARFIMA Model to Forecast Kijang Emas (Gold) Prices in Malaysia using MAE, RMSE and MAPE

Journal of Computing Research and Innovation ◽

10.24191/jcrinn.v6i3.225 ◽

2021 ◽

Vol 6 (3) ◽

pp. 22-33

Author(s):

Atiqa Nur Azza Mahmad Azan ◽

Nur Faizatul Auni Mohd Zulkifly Mototo ◽

Pauline Jin Wee Mah

Keyword(s):

Time Series ◽

Arima Model ◽

Time Series Models ◽

Monthly Average ◽

Arfima Models ◽

Gold Market ◽

Univariate Time Series ◽

The World ◽

Arfima Model ◽

Best Fit

Gold is known as the most valuable commodity in the world because it is a universal currency recognized by every single bank across the globe. Thus, many people were interested in investing gold since gold market was always steadier compared to other investment (Khamis and Awang, 2020). However, the credibility of gold was questionable due to the changes in gold prices caused by a variety of circumstances (Henriksen, 2018). Hence, information on the inflation of gold prices were needed to understand the trend in order to plan for the future in accordance with international gold price standards. The aim of this study was to identify the trend of Kijang Emas monthly average prices in Malaysia from the year 2010 to 2021, to determine the best fit time series model for Kijang Emas prices in Malaysia and using univariate time series models to forecast Kijang Emas prices in Malaysia. The ARIMA and ARFIMA models were used in this study to model and forecast the prices of gold (Kijang Emas) in Malaysia. Each of the actual monthly Kijang Emas prices for 2021 were found to be within the 95% predicted intervals for both the ARIMA and ARFIMA models. The performances for each model were checked by considering the values of MAE, RMSE and MAPE. From the findings, all the MAE, RMSE and MAPE values showed that the ARFIMA model emerged as the better model in forecasting the Kijang Emas prices in Malaysia compared to the ARIMA model.

Download Full-text

Comparing classic time series models and the LSTM recurrent neural network: An application to S&P 500 stocks

Finance, Markets and Valuation ◽

10.46503/zvbs2781 ◽

2020 ◽

Vol 6 (2) ◽

pp. 137-148

Author(s):

J. Oliver Muncharaz

Keyword(s):

Neural Network ◽

Neural Networks ◽

Time Series ◽

Stock Market ◽

Recurrent Neural Network ◽

Stock Prices ◽

Arima Model ◽

Time Series Models ◽

Prediction Errors ◽

The Creation

In the financial literature, there is great interest in the prediction of stock prices. Stock prediction is necessary for the creation of different investment strategies, both speculative and hedging ones. The application of neural networks has involved a change in the creation of predictive models. In this paper, we analyze the capacity of recurrent neural networks, in particular the long short-term recurrent neural network (LSTM) as opposed to classic time series models such as the Exponential Smooth Time Series (ETS) and the Arima model (ARIMA). These models have been estimated for 284 stocks from the S&P 500 stock market index, comparing the MAE obtained from their predictions. The results obtained confirm a significant reduction in prediction errors when LSTM is applied. These results are consistent with other similar studies applied to stocks included in other stock market indices, as well as other financial assets such as exchange rates.

Download Full-text