房屋市場中的租賃與買賣交易行為長期受到政策調控、經濟景氣等多重因素影響，展現出具時間演變性的複雜趨勢。然而，既有研究多聚焦於橫斷面分析或短期交易的單一特徵進行預測，對於長期交易資料中多面向特徵的趨勢變化與趨勢模式間的關聯性仍缺乏深入的探討。
本研究結合序列模式探勘與模式間關聯規則兩項技術，針對 2014 至 2023 年全台房屋租賃與買賣資料進行分析。研究首先將原始資料依縣市與年度進行時間序列化，建立涵蓋交易量、單價、面積等多項特徵的趨勢序列。接著透過 PrefixSpan 演算法挖掘長期中反覆出現的交易特徵趨勢，並進一步以模式間關聯規則分析趨勢之間的時間演變關係，探討租賃與買賣兩種交易特徵趨勢彼此在時間順序上的演變邏輯與潛在關聯。
研究結果顯示，透過本研究設計的趨勢表示方式與序列分析流程，不僅可以有效掌握房屋租賃與買賣交易中具有代表性的交易特徵趨勢模式，亦能從特徵趨勢模式之中發現明確的時間遞移關係，顯示趨勢模式之間具有潛在的順序關聯性，而非獨立發展。此一發現不僅說明了房屋市場行為背後的演變邏輯，也突破了既有傳統的趨勢分析方式，擴展序列模式間關聯分析在房屋市場趨勢研究中的應用，填補了過往對趨勢間關聯性的探討不足。

The housing market's rental and sales transactions have long been influenced by various factors such as government policies and economic conditions, exhibiting complex trends with temporal evolution. However, existing studies mostly focus on cross-sectional analyses or short-term predictions based on single transaction features, lacking in-depth exploration of long-term trend changes and inter-pattern relationships among multiple transaction characteristics.
This study integrates sequential pattern mining and inter-pattern association rule techniques to analyze nationwide housing rental and sales data in Taiwan from 2014 to 2023. The raw data is first transformed into time series by city and year, constructing trend sequences that encompass multiple features such as transaction volume, unit price, and floor area. The PrefixSpan algorithm is then employed to uncover recurring transaction trend patterns over the long term, followed by the application of inter-pattern association rules to analyze the temporal relationships between trends, aiming to uncover the underlying sequential logic and potential associations between rental and sales transaction patterns.
The results show that, through the proposed trend representation and sequential analysis
framework, the study effectively captures representative transaction trend patterns in rental and sales markets, and further reveals clear temporal transition relationships among them. These findings indicate that such trend patterns follow a structured sequential order rather than evolving independently. This discovery not only reveals the temporal logic underlying market behavior but also advances beyond traditional trend analytical approaches, extending the
application of inter-pattern association analysis in housing market trend research and addressing the existing gap in understanding trend-to-trend relationships.

[1] OECD, Brick by Brick: Building Better Housing Policies. Paris: OECD Publishing, 2021.
[2] Global Property Guide, "Taiwan's residential real estate market analysis," 2024. [Online].
Available: https://www.globalpropertyguide.com/asia/taiwan/price-history
[3] Y. L. Chen, "The factors and implications of rising housing prices in Taiwan," Brookings
Institution, 2016. [Online]. Available: https://www.brookings.edu/articles/the-factors-and
implications-of-rising-housing-prices-in-taiwan/
[4] 內 政 部 不 動 產 交 易 實 價 查 詢 服務網 , 2025. [Online]. Available:
https://lvr.land.moi.gov.tw
[5] 國家發展委員會景氣指標查詢系統, 2025. [Online]. Available: https://index.ndc.gov.tw
[6] 內政部戶政司全球資訊網, 2025. [Online]. Available: https://www.ris.gov.tw
[7] A. Belke and J. Keil, "Fundamental determinants of real estate prices: A cross-sectional
analysis of German regions," International Economics and Economic Policy, vol. 15, no.
2, pp. 349-373, 2018.
[8] K. Tsatsaronis and H. Zhu, "What drives housing price dynamics: cross-country evidence,"
BIS Quarterly Review, pp. 65-78, Mar. 2004.
[9] D. E. Rapach and J. K. Strauss, "Differences in housing price forecastability across US
states," International Journal of Forecasting, vol. 25, no. 2, pp. 351-372, 2009.
[10] Environmental Systems Research Institute, "Data classification methods," ArcGIS Pro
Documentation,
2024.
[Online].
Available:
https://pro.arcgis.com/en/pro
app/latest/help/mapping/layer-properties/data-classification-methods.htm
[11] U. M. Fayyad and K. B. Irani, "Multi-interval discretization of continuous-valued
attributes for classification learning," in Proc. 13th Int. Joint Conf. on Artificial
Intelligence, Chambéry, France, 1993, pp. 1022-1027.
[12] J. W. Tukey, Exploratory Data Analysis. Reading, MA: Addison-Wesley, 1977.
49
[13] C. Leys, C. Ley, O. Klein, P. Bernard, and L. Licata, "Detecting outliers: Do not use
standard deviation around the mean, use absolute deviation around the median," Journal
of Experimental Social Psychology, vol. 49, no. 4, pp. 764-766, 2013.
[14] D. C. Hoaglin, B. Iglewicz, and J. W. Tukey, "Performance of some resistant rules for
outlier labeling," Journal of the American Statistical Association, vol. 81, no. 396, pp. 991
999, Dec. 1986.
[15] W. H. Kruskal and W. A. Wallis, “Use of ranks in one-criterion variance analysis,” Journal
of the American Statistical Association, vol. 47, no. 260, pp. 583–621, 1952.
[16] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Boston,
MA: Morgan Kaufmann, 2011.
[17] R. Agrawal, T. Imielinski, and A. Swami, "Mining association rules between sets of items
in large databases," in Proc. 1993 ACM SIGMOD Int. Conf. Management of Data,
Washington, DC, USA, 1993, pp. 207-216.
[18] J. Pei et al., "Mining sequential patterns by pattern-growth: the PrefixSpan approach,"
IEEE Trans. Knowledge and Data Engineering, vol. 16, no. 11, pp. 1424-1440, Nov. 2004.
[19] J. Pei et al., "PrefixSpan: mining sequential patterns efficiently by prefix-projected pattern
growth," in Proc. 17th Int. Conf. Data Engineering, Heidelberg, Germany, 2001, pp. 215
224.