A TOPSIS Approach of Ranking Classifiers for Stock Index Price Movement Prediction

Dash, Rajashree; Samal, Sidharth; Rautray, Rasmita; Dash, Rasmita

doi:10.1007/978-981-13-0514-6_63

Cited by 9 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…TOPSIS sendiri hingga saat ini telah memiliki lebih dari 4500 sitasi resmi yang menjadikan metode ini selain banyak digunakan juga terbukti secara empiris mampu fleksibel dalam melakukan pemecahan beragam masalah [10]. Dalam penelitian yang sejenis, TOPSIS juga pernah digunakan untuk melakukan prediksi di bursa saham [11], [12], namun pada kasus tersebut lebih terfokus kepada prediksi indeks, bukan pada pemilihan emiten saham seperti yang dilakukan di dalam penelitian ini.…”

Section: Pendahuluanunclassified

Prototipe Pendukung Keputusan Pemilihan Saham Jangka Pendek Dengan Kriteria Majemuk

2021

View full text Add to dashboard Cite

Perdagangan dalam bursa efek, khususnya Bursa Efek Indonesia (BEI) telah meningkat pesat, terlebih dalam masa pandemi Covid-19. Volume transaksi telah menunjukkan peningkatan yang cukup pesat dan menjadi justifikasi bahwa perdagangan bursa lebih didominasi oleh transaksi saham jangka pendek. Maka kebutuhan analisis pembelian saham jangka pendek menjadi penting agar risiko kerugian trader dapat diminimalkan. Alat bantu analisis memanfaatkan TA yang disederhanakan agar menjadi pendukung keputusan aksi jual beli. Dalam artikel ini, disajikan hasil dengan menggunakan metode TOPSIS berdasarkan fleksibilitas nilai yang bisa diterapkan pada kriteria secara majemuk. Kriteria yang dipilih merupakan hasil dari wawancara dengan dua trader profesional yaitu posisi candlestick di atas garis EMA, lonjakan volume transaksi perdagangan atau spike volume, kondisi uptrend yang secara otomatis menjadi benefit serta likuiditas dari volume perdagangan. Hasil dari implementasi dengan pembuatan prototipe aplikasi berbasis web menunjukkan hasil yang cukup akurat setelah dilakukan backtest pada akhir September 2021. Namun masih perlu dilakukan backtest dengan periode yang berbeda karena anomali dalam bursa saham Indonesia yang seringkali bersifat volatile. Salah satu keunggulan dari prototipe ini adalah kebebasan untuk pemilihan kriteria dan nilai yang dimasukkan oleh pengguna dibandingkan mayoritas bot yang secara kaku menetapkan kriteria berdasarkan indikator TA.

show abstract

Section: Pendahuluanunclassified

Prototipe Pendukung Keputusan Pemilihan Saham Jangka Pendek Dengan Kriteria Majemuk

2021

View full text Add to dashboard Cite

show abstract

“…As a result, the determination of activation function necessitates additional analysis. Furthermore, while researchers have investigated the performance of many predictors or classifiers using a single criterion such as MSE or accuracy, assessing predictor performance using multiple criteria can result in a robust and reliable output (Kou et al 2012) and an MCDMbased analysis may provide robust outcome (Dash et al 2018(Dash et al , 2019Mehdiyev et al 2016;Samal and Dash 2021a). Another shortcoming of ELM and OSELM is that their input weights are arbitrary, which might lead to inferior results.…”

Section: Introductionmentioning

confidence: 99%

Developing a novel stock index trend predictor model by integrating multiple criteria decision-making with an optimized online sequential extreme learning machine

Samal

Dash

2022

Granul. Comput.

Self Cite

View full text Add to dashboard Cite

It has always been the goal of many researchers to gain a thorough understanding of the patterns in the stock market and forecast the trends it will follow. The use of an advanced forecasting model can assist with accurately forecasting the future price of stocks, their fluctuations in the markets, as well as make profits in trading. With this motivation, in this study, a novel stock index trend predictor model is designed by integrating Multiple Criteria Decision-Making (MCDM) with an optimized Online Sequential Extreme Learning Machine (OSELM). Forecasting the future stock index prices and analyzing the upward or downward trends of these price forecasts are the two objectives of the proposed model. As the performance of OSELM is heavily dependent on the activation functions used in it, suitable selection of the activation function for OSELM is addressed as a MCDM problem. According to this approach, the trend prediction performance of six popular activation functions is assessed based on five regression-based and five classification-based criteria. In this investigation, three MCDM approaches are used to assess the performance matrix and determine which activation function is the best for OSELM based on six alternative models and ten criteria. To further optimize OSELM's performance, a hybrid crow search algorithm (hCSA) is incorporated in its training phase. By introducing the chaotic map and mutation operator in position update scheme and catfish behavior in the search process of original CSA, the proposed hCSA is able to achieve the right balance between exploration and exploitation improving the convergence. The proposed trend predictor model is empirically evaluated over historical data of three stock indices such as BSE SENSEX, S&P 500 and DJIA collected during pre-COVID and COVID time frame. In most of the test cases, the hCSA-OSELM model outperforms the state-of-the-art baseline models in terms of all evaluation criteria. When compared to the second-best baseline model, the suggested model is able to achieve the MSE improvements of 4–6%, 25–31%, and accuracy improvements of 0.4–0.8%, 0.9–1.3% over the pre-COVID and COVID time-frames, respectively. The statistical test also reveals the better performance of the proposed model. The robust and reliable MCDM-based model selection, superior prediction and classification outcomes clearly reveal that the proposed model can be used for financial time-series forecasting amid daily volatility as well as highly volatile markets.

show abstract

An Empirical Comparison of TOPSIS and VIKOR for Ranking Decision-Making Models

Samal¹,

Dash²

2022

Smart Innovation, Systems and Technologies

View full text Add to dashboard Cite

A TOPSIS Approach of Ranking Classifiers for Stock Index Price Movement Prediction

Cited by 9 publications

References 11 publications

Prototipe Pendukung Keputusan Pemilihan Saham Jangka Pendek Dengan Kriteria Majemuk

Prototipe Pendukung Keputusan Pemilihan Saham Jangka Pendek Dengan Kriteria Majemuk

Developing a novel stock index trend predictor model by integrating multiple criteria decision-making with an optimized online sequential extreme learning machine

An Empirical Comparison of TOPSIS and VIKOR for Ranking Decision-Making Models

Contact Info

Product

Resources

About