• 沒有找到結果。

立 政 治 大 學

N a tio na

l C h engchi U ni ve rs it y

第五章 、結論與建議

5.1 研究結論

CMoney 財經新聞為公開取得之資訊,內容相當豐富與完整,對使用者來說 裡面蘊藏了許多的資訊,然而過往很多的財務預警之研究很少利用這類文本資料 做分析與預測,本研究將文本新聞的非結構化指標納入模型的考量因素中,再加 上依據 Altman(2000)所提出之 ZETA 模型的七大類財務比率指標來建立財務預警 模型,依實驗結果來看文本新聞的非結構化指標對模型來說都有顯著的影響,由 此可知財經新聞的多寡與情緒的正負,是能夠視為判斷上市公司是否有不良財務 狀況發生的依據。

本研究利用 KNN、Naive Bayes、SVM 三種演算法對 CMoney 財經新聞進行情 緒分析並觀察其分類準確度,實驗結果顯示採用支援向量機(SVM)所進行之情緒 分類準確率是較高的,且經過交叉驗證與統計檢定結果是有顯著差異的,也驗證 Joachims(1988)所提出 SVM 為最適合文本分類的演算法,以供未來需進行文本情 緒分析之研究做參考。

在建立財務預警模型之部分,本研究採用 Logistic Regression (邏輯式回 歸)與 Random Forests(隨機森林)與隱藏馬可夫模型(HMM)三種演算法結合情緒 分析結果建立模型,並使用 k-fold cross-validation 進行交叉驗證觀察其準確 率,實驗結果顯示 Logistic Regression 所建立之模型之準確率為 0.75 左右,

而 Random Forests 與 HMM 準確率都高過 0.77,由平均準確率來看 Random Forests 比起其他兩種演算法有較佳的預測力,且三種演算法都優於原本 Altman Zeta model 的準確率(平均準確率 0.696),由此可見本研究之演算法可以改善原本的 財務預警模型,本研究也分析了三種演算法的優點與缺點以供未來需要從事財務 預警之研究參考。

‧ 國

立 政 治 大 學

N a tio na

l C h engchi U ni ve rs it y

知,ROA 稅後息前、收入標準差、新聞總量、正向新聞數、負向新聞數這 5 個變 量具有統計學上的意義,顯著性都小於或等於 P(0.1),可得到這 5 個自變數對 財務預警模型所預測的結果是有顯著影響的,而在之中的三個變數皆為情緒變 數,可知情緒變數在預測模型中是有影響力,本研究挑選顯著性最強 P(0.004) 的變數(負向新聞數)為訓練隱藏馬可夫模型的觀察序列。

5.2 研究貢獻

本研究之貢獻為結合財經新聞之情緒分析指標,驗證其對財務預警模型之影 響,在情緒分析之演算法方面驗證了 Joachims(1998)所提出 SVM 為最適合文本 分類的演算法,再與結構化財務比率做結合建立起財務預警模型,並驗證公司內 部的財務指標與外部的財經新聞指標是如何影響公司之財務狀況。本研究另一貢 獻為應用隱藏馬可夫模型與隨機森林於財務預警的領域,並比對以 Altman Zeta Model 所預測的財務狀況,經實驗結果得知本研究所建立的模型優於前者(Zeta model),並擁有較佳的預測準確率,然而因本實驗樣本數據屬於小樣本的分析,

較適用於隨機森林的隨機採樣方式,試驗結果也顯示隨機森林結合情緒分析的演 算法準確率是最佳的。

5.3 未來建議

未來研究建議部分,因中文財經專業情緒字典之不足,未來研究可以擴充字 典,搜尋更多文字探勘的論文與文章進行字典的擴充以提升分類精準度,而因此 研究只分析 2015 至 2017 之公司為樣本,屬於短期且小樣本之分析,未來研究可 以將時間框架拉長,觀察公司財務狀況之長期趨勢,並利用時間序列之方式觀察 其準確度,然而不同的產業各有不同的特性,也因每個產業的不同,財務預警的 判斷標準也會不一樣,可以建議在未來的研究中再細分成不同產業的財務預警研 究,以提升預測的正確性與合理性,另外本研究的財務指標是以季為單位,而文 本新聞則是每天都有,可能新聞產出的時間與財報指標的產出之間有時間差,使 判斷並不客觀,未來可以將此時間差考慮進去,使財務預警模型更加完整。

Akhtar, S., Faff, R., Oliver, B., & Subrahmanyam, A. (2011). The power of bad: The negativity bias in Australian consumer sentiment announcements on stock returns. Journal of Banking & Finance, 35(5), 1239-1249.

Altman, E. I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The journal of finance, 23(4), 589-609.

Altman, E. I. (2000). Predicting financial distress of companies: revisiting the Z-score and ZETA models. Stern School of Business, New York University, 9-12.

Altman, E. I., Iwanicz‐Drozdowska, M., Laitinen, E. K., & Suvas, A. (2017).

Financial Distress Prediction in an International Context: A Review and Empirical Analysis of Altman's Z‐Score Model. Journal of International Financial Management & Accounting, 28(2), 131-171.

Batal, I., & Hauskrecht, M. (2009). Boosting KNN text classification accuracy by using supervised term weighting schemes. Paper presented at the Proceedings of the 18th ACM conference on Information and knowledge management.

Beaver, W. H. (1966). Financial ratios as predictors of failure. Journal of accounting research, 71-111.

Bijalwan, V., Kumar, V., Kumari, P., & Pascual, J. (2014). KNN based machine learning approach for text and document mining. International Journal of Database Theory and Application, 7(1), 61-70.

Blunsom, P. (2004). Hidden markov models. Lecture notes, August, 15, 18-19.

Cecchini, M., Aytug, H., Koehler, G. J., & Pathak, P. (2010). Making words work:

Using financial text as a predictor of financial events. Decision support systems, 50(1), 164-175.

Chen, W.-S., & Du, Y.-K. (2009). Using neural networks and data mining techniques for the financial distress prediction model. Expert systems with applications, 36(2), 4075-4086.

Clatworthy, M. A., & Jones, M. J. (2006). Differential patterns of textual characteristics and company performance in the chairman's statement.

Accounting, Auditing & Accountability Journal, 19(4), 493-511.

Dhar, S., Mukherjee, T., & Ghoshal, A. K. (2010). Performance evaluation of Neural Network approach in financial prediction: Evidence from Indian Market.

Paper presented at the Communication and Computational Intelligence (INCOCCI), 2010 International Conference on.

Eddy, S. R. (1996). Hidden markov models. Current opinion in structural biology,

Fan, A., & Palaniswami, M. (2000). Selecting bankruptcy predictors using a support vector machine approach. Paper presented at the Neural Networks, 2000.

IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on.

Frazier, K. B., Ingram, R. W., & Tennyson, B. M. (1984). A methodology for the analysis of narrative accounting disclosures. Journal of accounting research, 318-331.

Frydman, H., Altman, E. I., & KAO, D. L. (1985). Introducing recursive partitioning for financial classification: the case of financial distress. The journal of finance, 40(1), 269-291.

Geng, R., Bose, I., & Chen, X. (2015). Prediction of financial distress: An empirical study of listed Chinese companies using data mining. European journal of operational research, 241(1), 236-247.

Hassan, M. R., & Nath, B. (2005). Stock market forecasting using hidden Markov model: a new approach. Paper presented at the Intelligent Systems Design and Applications, 2005. ISDA'05. Proceedings. 5th International Conference on.

Hooda, N., Bawa, S., & Rana, P. S. (2018). Fraudulent Firm Classification: A Case Study of an External Audit. Applied Artificial Intelligence, 32(1), 48-64.

Joachims, T. (1998). Text categorization with support vector machines: Learning with many relevant features. Paper presented at the European conference on

machine learning.

Li, Q., Wang, T., Gong, Q., Chen, Y., Lin, Z., & Song, S.-k. (2014). Media-aware quantitative trading based on public Web information. Decision support systems, 61, 93-105.

Li, Z., Crook, J., & Andreeva, G. (2014). Chinese companies distress prediction: an application of data envelopment analysis. Journal of the Operational Research Society, 65(3), 466-479.

Loughran, T., & McDonald, B. (2011). When is a liability not a liability? Textual analysis, dictionaries, and 10‐Ks. The journal of finance, 66(1), 35-65.

Magnusson, C., Arppe, A., Eklund, T., Back, B., Vanharanta, H., & Visa, A. (2005).

The language of quarterly reports as an indicator of change in the company’s financial status. Information & Management, 42(4), 561-574.

Meyer, P. A., & Pifer, H. W. (1970). Prediction of bank failures. The journal of finance, 25(4), 853-868.

Odom, M. D., & Sharda, R. (1990). A neural network model for bankruptcy prediction.

Paper presented at the Neural Networks, 1990., 1990 IJCNN International Joint Conference on.

Ohlson, J. A. (1980). Financial ratios and the probabilistic prediction of bankruptcy.

Journal of accounting research, 109-131.

Petersen, M. A. (2004). Information: Hard and soft. Northwestern University.

Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257-286.

Srivastava, Kundu, Sural, & Majumdar. (2008). Credit card fraud detection using hidden Markov model. . IEEE Transactions on dependable and secure computing, 5(1), 37-48.

Tam, K. Y., & Kiang, M. Y. (1992). Managerial applications of neural networks: the case of bank failure predictions. Management science, 38(7), 926-947.

Tongshui, X., & Yanli, Z. (2015). The Research on Financial Early Warning of China’s New Energy Listed Company. International Journal of Business and Management, 10(9), 136.

Tsai, M.-F., Wang, C.-J., & Chien, P.-C. (2016). Discovering finance keywords via continuous-space language models. ACM Transactions on Management Information Systems (TMIS), 7(3), 7.

Van Gestel, T., Baesens, B., Suykens, J. A., Van den Poel, D., Baestaens, D.-E., &

Willekens, M. (2006). Bayesian kernel based classification for financial distress detection. European journal of operational research, 172(3), 979-1003.

Wanke, P., Barros, C. P., & Faria, J. R. (2015). Financial distress drivers in Brazilian banks: A dynamic slacks approach. European journal of operational research, 240(1), 258-268.

Yu, Y., Duan, W., & Cao, Q. (2013). The impact of social and conventional media on firm equity value: A sentiment analysis approach. Decision support systems, 55(4), 919-926.

Zmijewski, M. E. (1984). Methodological issues related to the estimation of financial distress prediction models. Journal of accounting research, 59-82.

王憶紅. (2017). 興航下市走入歷史. 自由時報.

‧ 國

立 政 治 大 學

N a tio na

l C h engchi U ni ve rs it y

179-181.

涉環電內線交易 日月光發言人 2 家族成員收押. (2017). 東森新聞.

袁延壽. (2017). 冠德掏空案起訴 3 人 根基、冠德:尊重司法調查. 工商時報.

袁顥庭. (2016). 介面淨值為負 8 月 3 日下市. 工商時報.

莊丙農. (2017). 《證交所》台一財報不實,10 月中旬前恐下市. 時報資訊.

陳志賢. (2017). 必翔又傳弊案 負責人再遭搜索. 工商時報.

黃鳳丹. (2017). 新焦點-DR 6/27 下市. 工商時報

楊佩琪. (2016). 驚爆!中信金重大弊案 辜仲諒恐涉近百億資金掏空. 東森 新聞.

楊政郡. (2015). 上市成霖公司董事及顧問 涉內線交易被起訴. 自由時報.

劉妍辰. (2010). 企業年報文字資訊影響資金成本, 股價報酬波動性與分析師 盈餘預測準確度之研究. 臺灣大學會計學研究所學位論文, 1-88.

賴佩璇. (2017). 聯發科收購立錡爆內線交易 檢方今起訴兩人. 聯合報.

謝君臨. (2017a). 涉內線交易避損 益航財務長謝妙龍起訴. 自由時報.

謝君臨. (2017b). 涉掏空 7000 萬 宏正科前法務長被押. 自由時報.

相關文件