Analysis and forecasting of IPO underpricing

Esfahanipour, Akbar; Goodarzi, Milad; Jahanbin, Reza

doi:10.1007/s00521-015-1884-1

Cited by 10 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These authors try to predict the post-issue market price using artificial neural networks. More recently, Reber et al [3], Meng [4], Chen [5], and Esfahanipour et al [6] followed suit with the same technique. This line was…”

Section: Introductionmentioning

confidence: 99%

Random Forest Prediction of IPO Underpricing

2017

View full text Add to dashboard Cite

Abstract:The prediction of initial returns on initial public offerings (IPOs) is a complex matter. The independent variables identified in the literature mix strong and weak predictors, their explanatory power is limited, and samples include a sizable number of outliers. In this context, we suggest that random forests are a potentially powerful tool. In this paper, we benchmark this algorithm against a set of eight classic machine learning algorithms. The results of this comparison show that random forests outperform the alternatives in terms of mean and median predictive accuracy. The technique also provided the second smallest error variance among the stochastic algorithms. The experimental work also supports the potential of random forests for two practical applications: IPO pricing and IPO trading.

show abstract

Section: Introductionmentioning

confidence: 99%

Random Forest Prediction of IPO Underpricing

2017

View full text Add to dashboard Cite

show abstract

“…However, various market environments could not be verified due to the limitation of using data for a relatively short period from 1996 to 1999. Quintana et al [15] presented strategies for IPO underpricing prediction and Esfahanipour et al [16] examined probability of withdrawal and underpricing of IPO stock using neural network and fuzzy regression. They found that the probability of IPO withdrawal plays an important role in precise evaluation of underpricing.…”

Section: Related Studiesmentioning

confidence: 99%

A Machine Learning Portfolio Allocation System for IPOs in Korean Markets Using GA-Rough Set Theory

et al. 2019

View full text Add to dashboard Cite

An initial public offering (IPO) is a type of public offering in which a company’s shares are sold to institutional and individual investors. While the majority of studies on IPOs have focused on the efficiency of raising capital and price adequacy in IPOs, studies on portfolio allocation strategies for IPO stocks are relatively scarce. This paper develops a machine learning investment strategy for IPO stocks based on rough set theory and a genetic algorithm (GA-rough set theory). To reduce issues of information asymmetry, we use nonfinancial data that are publicly available to individual and institutional investors in the IPO process. Based on the rule sets generated from the training sets, we conduct 120 tests with various conditions involving the target days and the partition of the training and testing sets, and we find excess returns of the constructed portfolios compared to the benchmark portfolios. Investors in IPO stocks can formulate more efficient investment strategies using our system. In this sense, the system developed in this paper contributes to the efficiency of financial markets and helps achieve sustained economic growth.

show abstract

“…However, soft computing models seem to be more appropriate for modeling the noisy, nonlinear and complex behavior of the stock markets [54][55][56][57][58]. In the literature, there are some studies on the soft computing methods such as artificial neural networks [3,59], evolutionary algorithms [60][61][62][63], support vector machines [64] and fuzzy logic [65][66][67][68] for stock selection problem.…”

Section: Stock Selection Based On the Fundamental Analysismentioning

confidence: 99%

A modular Takagi-Sugeno-Kang (TSK) system based on a modified hybrid soft clustering for stock selection

Mousavi¹,

Esfahanipour²,

Zarandi³

2019

Scientia Iranica

Self Cite

View full text Add to dashboard Cite

A modular Takagi-Sugeno-Kang (TSK) system based on a modified hybrid soft clustering for stock selection This study presents a new hybrid intelligent system with ensemble learning for stock selection using the fundamental information of companies. The system uses the selected financial ratios of each company as the input variables and ranks the candidate stocks. Due to the different characteristics of the companies from different activity sectors, modular system for stock selection may show a better performance in comparison with an individual system. Here, a hybrid soft clustering algorithm is proposed to eliminate the noise and partition the input data set into more homogeneous overlapped subsets. The proposed clustering algorithm benefits from the strengths of the fuzzy, possibilistic and rough clustering to develop a modular system. An individual Takagi-Sugeno-Kang (TSK) system is extracted from each subset using an artificial neural network and genetic algorithm. To integrate the outputs of the individual TSK systems, a new weighted ensemble strategy is proposed. The performance of the proposed system is evaluated among 150 companies listed on Tehran Stock Exchange (TSE) regarding information coefficient, classification accuracy and appreciation in stock price. The experimental results show that the proposed modular TSK system significantly outperforms the single TSK system as well as the other ensemble models using different decomposition and combination strategies.

show abstract

Analysis and forecasting of IPO underpricing

Cited by 10 publications

References 27 publications

Random Forest Prediction of IPO Underpricing

Random Forest Prediction of IPO Underpricing

A Machine Learning Portfolio Allocation System for IPOs in Korean Markets Using GA-Rough Set Theory

A modular Takagi-Sugeno-Kang (TSK) system based on a modified hybrid soft clustering for stock selection

Contact Info

Product

Resources

About