Hidden fuzzy Markov model for the Time series Forecasting: an Example of Taiwan inward Visitor
碩士 === 明新科技大學 === 管理研究所碩士班 === 105 === This study proposes Hidden-state Markov Model for forecasting the Taiwan inward visitor. The MAPE and MSE are used to evaluate the predictive error of the model proposed. The time series data is obtained from the Tourism Bureau and Taiwan Economic Journal from...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2017
|
Online Access: | http://ndltd.ncl.edu.tw/handle/39f3k8 |
id |
ndltd-TW-105MHIT0457010 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-105MHIT04570102019-05-15T23:24:31Z http://ndltd.ncl.edu.tw/handle/39f3k8 Hidden fuzzy Markov model for the Time series Forecasting: an Example of Taiwan inward Visitor 隱藏式模糊馬可夫模型於時間序列預測-以來台旅客人數為例 Shih, Wei-Yuan 史崴元 碩士 明新科技大學 管理研究所碩士班 105 This study proposes Hidden-state Markov Model for forecasting the Taiwan inward visitor. The MAPE and MSE are used to evaluate the predictive error of the model proposed. The time series data is obtained from the Tourism Bureau and Taiwan Economic Journal from January 1984 to December 2015 including 384 monthly data sets. The empirical result indicates that the relationship between Taiwan inward visitor and export gross rate, import gross rate, unemployment rate, consumer price index and misery index reaches the long-term equilibrium. For the model predictive purposes, when the sample data is smooth and then the 2-factor model has better predictive performance than the 3 or 4-factor model. On the opposite, when the sample data is not smooth and show with some extreme values, the 3-factor model has better predictive performance than the others. Wang, Hsien-Lun 王賢崙 2017 學位論文 ; thesis 70 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 明新科技大學 === 管理研究所碩士班 === 105 === This study proposes Hidden-state Markov Model for forecasting the Taiwan inward visitor. The MAPE and MSE are used to evaluate the predictive error of the model proposed. The time series data is obtained from the Tourism Bureau and Taiwan Economic Journal from January 1984 to December 2015 including 384 monthly data sets. The empirical result indicates that the relationship between Taiwan inward visitor and export gross rate, import gross rate, unemployment rate, consumer price index and misery index reaches the long-term equilibrium. For the model predictive purposes, when the sample data is smooth and then the 2-factor model has better predictive performance than the 3 or 4-factor model. On the opposite, when the sample data is not smooth and show with some extreme values, the 3-factor model has better predictive performance than the others.
|
author2 |
Wang, Hsien-Lun |
author_facet |
Wang, Hsien-Lun Shih, Wei-Yuan 史崴元 |
author |
Shih, Wei-Yuan 史崴元 |
spellingShingle |
Shih, Wei-Yuan 史崴元 Hidden fuzzy Markov model for the Time series Forecasting: an Example of Taiwan inward Visitor |
author_sort |
Shih, Wei-Yuan |
title |
Hidden fuzzy Markov model for the Time series Forecasting: an Example of Taiwan inward Visitor |
title_short |
Hidden fuzzy Markov model for the Time series Forecasting: an Example of Taiwan inward Visitor |
title_full |
Hidden fuzzy Markov model for the Time series Forecasting: an Example of Taiwan inward Visitor |
title_fullStr |
Hidden fuzzy Markov model for the Time series Forecasting: an Example of Taiwan inward Visitor |
title_full_unstemmed |
Hidden fuzzy Markov model for the Time series Forecasting: an Example of Taiwan inward Visitor |
title_sort |
hidden fuzzy markov model for the time series forecasting: an example of taiwan inward visitor |
publishDate |
2017 |
url |
http://ndltd.ncl.edu.tw/handle/39f3k8 |
work_keys_str_mv |
AT shihweiyuan hiddenfuzzymarkovmodelforthetimeseriesforecastinganexampleoftaiwaninwardvisitor AT shǐwǎiyuán hiddenfuzzymarkovmodelforthetimeseriesforecastinganexampleoftaiwaninwardvisitor AT shihweiyuan yǐncángshìmóhúmǎkěfūmóxíngyúshíjiānxùlièyùcèyǐláitáilǚkèrénshùwèilì AT shǐwǎiyuán yǐncángshìmóhúmǎkěfūmóxíngyúshíjiānxùlièyùcèyǐláitáilǚkèrénshùwèilì |
_version_ |
1719145740568100864 |