Bankruptcy Forecasting Model using AdaBoost: A Focus on Construction Companies (적응형 부스팅을 이용한 파산 예측 모형: 건설업을 중심으로)
-
- Journal of Intelligence and Information Systems
- /
- v.20 no.1
- /
- pp.35-48
- /
- 2014
According to the 2013 construction market outlook report, the liquidation of construction companies is expected to continue due to the ongoing residential construction recession. Bankruptcies of construction companies have a greater social impact compared to other industries. However, due to the different nature of the capital structure and debt-to-equity ratio, it is more difficult to forecast construction companies' bankruptcies than that of companies in other industries. The construction industry operates on greater leverage, with high debt-to-equity ratios, and project cash flow focused on the second half. The economic cycle greatly influences construction companies. Therefore, downturns tend to rapidly increase the bankruptcy rates of construction companies. High leverage, coupled with increased bankruptcy rates, could lead to greater burdens on banks providing loans to construction companies. Nevertheless, the bankruptcy prediction model concentrated mainly on financial institutions, with rare construction-specific studies. The bankruptcy prediction model based on corporate finance data has been studied for some time in various ways. However, the model is intended for all companies in general, and it may not be appropriate for forecasting bankruptcies of construction companies, who typically have high liquidity risks. The construction industry is capital-intensive, operates on long timelines with large-scale investment projects, and has comparatively longer payback periods than in other industries. With its unique capital structure, it can be difficult to apply a model used to judge the financial risk of companies in general to those in the construction industry. Diverse studies of bankruptcy forecasting models based on a company's financial statements have been conducted for many years. The subjects of the model, however, were general firms, and the models may not be proper for accurately forecasting companies with disproportionately large liquidity risks, such as construction companies. The construction industry is capital-intensive, requiring significant investments in long-term projects, therefore to realize returns from the investment. The unique capital structure means that the same criteria used for other industries cannot be applied to effectively evaluate financial risk for construction firms. Altman Z-score was first published in 1968, and is commonly used as a bankruptcy forecasting model. It forecasts the likelihood of a company going bankrupt by using a simple formula, classifying the results into three categories, and evaluating the corporate status as dangerous, moderate, or safe. When a company falls into the "dangerous" category, it has a high likelihood of bankruptcy within two years, while those in the "safe" category have a low likelihood of bankruptcy. For companies in the "moderate" category, it is difficult to forecast the risk. Many of the construction firm cases in this study fell in the "moderate" category, which made it difficult to forecast their risk. Along with the development of machine learning using computers, recent studies of corporate bankruptcy forecasting have used this technology. Pattern recognition, a representative application area in machine learning, is applied to forecasting corporate bankruptcy, with patterns analyzed based on a company's financial information, and then judged as to whether the pattern belongs to the bankruptcy risk group or the safe group. The representative machine learning models previously used in bankruptcy forecasting are Artificial Neural Networks, Adaptive Boosting (AdaBoost) and, the Support Vector Machine (SVM). There are also many hybrid studies combining these models. Existing studies using the traditional Z-Score technique or bankruptcy prediction using machine learning focus on companies in non-specific industries. Therefore, the industry-specific characteristics of companies are not considered. In this paper, we confirm that adaptive boosting (AdaBoost) is the most appropriate forecasting model for construction companies by based on company size. We classified construction companies into three groups - large, medium, and small based on the company's capital. We analyzed the predictive ability of AdaBoost for each group of companies. The experimental results showed that AdaBoost has more predictive ability than the other models, especially for the group of large companies with capital of more than 50 billion won.
Vision and voice-based technologies are commonly utilized for human-robot interaction. But it is widely recognized that the performance of vision and voice-based interaction systems is deteriorated by a large margin in the real-world situations due to environmental and user variances. Human users need to be very cooperative to get reasonable performance, which significantly limits the usability of the vision and voice-based human-robot interaction technologies. As a result, touch screens are still the major medium of human-robot interaction for the real-world applications. To empower the usability of robots for various services, alternative interaction technologies should be developed to complement the problems of vision and voice-based technologies. In this paper, we propose the use of accelerometer-based gesture interface as one of the alternative technologies, because accelerometers are effective in detecting the movements of human body, while their performance is not limited by environmental contexts such as lighting conditions or camera's field-of-view. Moreover, accelerometers are widely available nowadays in many mobile devices. We tackle the problem of classifying acceleration signal patterns of 26 English alphabets, which is one of the essential repertoires for the realization of education services based on robots. Recognizing 26 English handwriting patterns based on accelerometers is a very difficult task to take over because of its large scale of pattern classes and the complexity of each pattern. The most difficult problem that has been undertaken which is similar to our problem was recognizing acceleration signal patterns of 10 handwritten digits. Most previous studies dealt with pattern sets of 8~10 simple and easily distinguishable gestures that are useful for controlling home appliances, computer applications, robots etc. Good features are essential for the success of pattern recognition. To promote the discriminative power upon complex English alphabet patterns, we extracted 'motion trajectories' out of input acceleration signal and used them as the main feature. Investigative experiments showed that classifiers based on trajectory performed 3%~5% better than those with raw features e.g. acceleration signal itself or statistical figures. To minimize the distortion of trajectories, we applied a simple but effective set of smoothing filters and band-pass filters. It is well known that acceleration patterns for the same gesture is very different among different performers. To tackle the problem, online incremental learning is applied for our system to make it adaptive to the users' distinctive motion properties. Our system is based on instance-based learning (IBL) where each training sample is memorized as a reference pattern. Brute-force incremental learning in IBL continuously accumulates reference patterns, which is a problem because it not only slows down the classification but also downgrades the recall performance. Regarding the latter phenomenon, we observed a tendency that as the number of reference patterns grows, some reference patterns contribute more to the false positive classification. Thus, we devised an algorithm for optimizing the reference pattern set based on the positive and negative contribution of each reference pattern. The algorithm is performed periodically to remove reference patterns that have a very low positive contribution or a high negative contribution. Experiments were performed on 6500 gesture patterns collected from 50 adults of 30~50 years old. Each alphabet was performed 5 times per participant using
User authentication based on ID and PW has been widely used. As the Internet has become a growing part of people' lives, input times of ID/PW have been increased for a variety of services. People have already learned enough to perform the authentication procedure and have entered ID/PW while ones are unconscious. This is referred to as the adaptive unconscious, a set of mental processes incoming information and producing judgements and behaviors without our conscious awareness and within a second. Most people have joined up for various websites with a small number of IDs/PWs, because they relied on their memory for managing IDs/PWs. Human memory decays with the passing of time and knowledges in human memory tend to interfere with each other. For that reason, there is the potential for people to enter an invalid ID/PW. Therefore, these characteristics above mentioned regarding of user authentication with ID/PW can lead to human vulnerabilities: people use a few PWs for various websites, manage IDs/PWs depending on their memory, and enter ID/PW unconsciously. Based on the vulnerability of human factors, a variety of information leakage attacks such as phishing and pharming attacks have been increasing exponentially. In the past, information leakage attacks exploited vulnerabilities of hardware, operating system, software and so on. However, most of current attacks tend to exploit the vulnerabilities of the human factors. These attacks based on the vulnerability of the human factor are called social-engineering attacks. Recently, malicious social-engineering technique such as phishing and pharming attacks is one of the biggest security problems. Phishing is an attack of attempting to obtain valuable information such as ID/PW and pharming is an attack intended to steal personal data by redirecting a website's traffic to a fraudulent copy of a legitimate website. Screens of fraudulent copies used for both phishing and pharming attacks are almost identical to those of legitimate websites, and even the pharming can include the deceptive URL address. Therefore, without the supports of prevention and detection techniques such as vaccines and reputation system, it is difficult for users to determine intuitively whether the site is the phishing and pharming sites or legitimate site. The previous researches in terms of phishing and pharming attacks have mainly studied on technical solutions. In this paper, we focus on human behaviour when users are confronted by phishing and pharming attacks without knowing them. We conducted an attack experiment in order to find out how many IDs/PWs are leaked from pharming and phishing attack. We firstly configured the experimental settings in the same condition of phishing and pharming attacks and build a phishing site for the experiment. We then recruited 64 voluntary participants and asked them to log in our experimental site. For each participant, we conducted a questionnaire survey with regard to the experiment. Through the attack experiment and survey, we observed whether their password are leaked out when logging in the experimental phishing site, and how many different passwords are leaked among the total number of passwords of each participant. Consequently, we found out that most participants unconsciously logged in the site and the ID/PW management dependent on human memory caused the leakage of multiple passwords. The user should actively utilize repudiation systems and the service provider with online site should support prevention techniques that the user can intuitively determined whether the site is phishing.
In this paper, we suggest an architecture of DS/CDMA tranceiver composed of one pilot channel used as reference and multiple traffic channels. The pilot channel-an unmodulated PN code-is used as the reference signal for synchronization of PN code and data demondulation. The coherent demodulation architecture is also exploited for the reverse link as well as for the forward link. Here are the characteristics of the suggested DS/CDMA system. First, we suggest an interlaced quadrature spreading(IQS) method. In this method, the PN coe for I-phase 1st channel is used for Q-phase 2nd channels and the PN code for Q-phase 1st channel is used for I-phase 2nd channel, and so on-which is quite different from the eisting spreading schemes of DS/CDMA systems, such as IS-95 digital CDMA cellular or W-CDMA for PCS. By doing IQS spreading, we can drastically reduce the zero crossing rate of the RF signals. Second, we introduce an adaptive threshold setting for the synchronization of PN code, an initial acquistion method that uses a single PN code generator and reduces the acquistion time by a half compared the existing ones, and exploit the state machines to reduce the reacquistion time Third, various kinds of functions, such as automatic frequency control(AFC), automatic level control(ALC), bit-error-rate(BER) estimator, and spectral shaping for reducing the adjacent channel interference, are introduced to improve the system performance. Fourth, we designed and implemented the DS/CDMA MODEM to be used for variable transmission rate applications-from 16Kbps to 1.024Mbps. We developed and confirmed the DS/CDMA MODEM architecture through mathematical analysis and various kind of simulations. The ASIC design was done using VHDL coding and synthesis. To cope with several different kinds of applications, we developed transmitter and receiver ASICs separately. While a single transmitter or receiver ASC contains three channels (one for the pilot and the others for the traffic channels), by combining several transmitter ASICs, we can expand the number of channels up to 64. The ASICs are now under use for implementing a line-of-sight (LOS) radio equipment.
W investigated the environmental factors and inhabiting biota such as macrophytes and zooplankton in 43 sites located on Jeju Island from May and June 2017 to evaluate the spread and ecosystem risk of dotted duckweed (landoltia punctata) which was recently found for the first time in Jeju Island. Dotted duckweeds were found in a total of 18 sites which tended to show low biomass of aquatic macrophyte species other than the dotted duckweed. We conducted a pattern analysis using SOM (Self-Organizing Map), which extracts information through competitive and adaptive properties, to analyze the effect of inhabiting biota on aquatic macrophytes such as the dotted duckweed and environmental factors. The SOM analysis showed that the inhabiting biota such as the zooplankton affected the biomass of aquatic macrophytes than they did the environmental factors. In particular, the biomass of dotted duckweed was positively related to plant-attached species (Alona, Chydorus, and Pleuroxus). Considering that low density of aquatic macrophytes covers the streams and wetlands on Jeju Island because of irregular water source and sharp change of water depth, the dotted duckweeds are likely to play an essential role as the vital habitat for micro-biota including zooplankton in wetlands and streams on Jeju Island. Furthermore, considering that organic matters are utilized as the primary food source in the areas occupied by dotted duckweed, dotted duckweeds have the role of being both habitat and food source. Although the dense growth of dotted duckweed adversely affects growth and development of some aquatic plants due to the shadow effect, it is due to the dominance of floating plants on the water surface should not be regarded as the risk of the dotted duckweed. In conclusion, the dotted duckweeds have spread and settled in most of the water systems on Jeju Island, their impact on inhabiting biota and the aquatic environment was minor. It is necessary to monitor the distribution and spread of dotted duckweeds in the inland areas outside of Jeju Island in the future.
The wall shear stress in the vicinity of end-to end anastomoses under steady flow conditions was measured using a flush-mounted hot-film anemometer(FMHFA) probe. The experimental measurements were in good agreement with numerical results except in flow with low Reynolds numbers. The wall shear stress increased proximal to the anastomosis in flow from the Penrose tubing (simulating an artery) to the PTFE: graft. In flow from the PTFE graft to the Penrose tubing, low wall shear stress was observed distal to the anastomosis. Abnormal distributions of wall shear stress in the vicinity of the anastomosis, resulting from the compliance mismatch between the graft and the host artery, might be an important factor of ANFH formation and the graft failure. The present study suggests a correlation between regions of the low wall shear stress and the development of anastomotic neointimal fibrous hyperplasia(ANPH) in end-to-end anastomoses. 30523 T00401030523 ^x Air pressure decay(APD) rate and ultrafiltration rate(UFR) tests were performed on new and saline rinsed dialyzers as well as those roused in patients several times. C-DAK 4000 (Cordis Dow) and CF IS-11 (Baxter Travenol) reused dialyzers obtained from the dialysis clinic were used in the present study. The new dialyzers exhibited a relatively flat APD, whereas saline rinsed and reused dialyzers showed considerable amount of decay. C-DAH dialyzers had a larger APD(11.70
The wall shear stress in the vicinity of end-to end anastomoses under steady flow conditions was measured using a flush-mounted hot-film anemometer(FMHFA) probe. The experimental measurements were in good agreement with numerical results except in flow with low Reynolds numbers. The wall shear stress increased proximal to the anastomosis in flow from the Penrose tubing (simulating an artery) to the PTFE: graft. In flow from the PTFE graft to the Penrose tubing, low wall shear stress was observed distal to the anastomosis. Abnormal distributions of wall shear stress in the vicinity of the anastomosis, resulting from the compliance mismatch between the graft and the host artery, might be an important factor of ANFH formation and the graft failure. The present study suggests a correlation between regions of the low wall shear stress and the development of anastomotic neointimal fibrous hyperplasia(ANPH) in end-to-end anastomoses. 30523 T00401030523 ^x Air pressure decay(APD) rate and ultrafiltration rate(UFR) tests were performed on new and saline rinsed dialyzers as well as those roused in patients several times. C-DAK 4000 (Cordis Dow) and CF IS-11 (Baxter Travenol) reused dialyzers obtained from the dialysis clinic were used in the present study. The new dialyzers exhibited a relatively flat APD, whereas saline rinsed and reused dialyzers showed considerable amount of decay. C-DAH dialyzers had a larger APD(11.70
Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.