Bankruptcy prediction based on financial ratios using Jordan Recurrent Neural Networks: a case study in Polish companies
01 May 2018-Vol. 1025, Iss: 1, pp 012098
TL;DR: This paper proposes the implementation of Jordan Recurrent Neural Networks (JRNN) to classify and predict corporate bankruptcy based on financial ratios with average success rate of 81.3785%.
Abstract: Complexity of bankruptcy causes the accurate models of bankruptcy prediction difficult to be achieved. Various prediction models have been developed to improve the accuracy of bankruptcy predictions. Machine learning has been widely used to predict because of its adaptive capabilities. Artificial Neural Networks (ANN) is one of machine learning which proved able to complete inference tasks such as prediction and classification especially in data mining. In this paper, we propose the implementation of Jordan Recurrent Neural Networks (JRNN) to classify and predict corporate bankruptcy based on financial ratios. Feedback interconnection in JRNN enable to make the network keep important information well allowing the network to work more effectively. The result analysis showed that JRNN works very well in bankruptcy prediction with average success rate of 81.3785%.
Citations
More filters
29 Aug 2021
TL;DR: In this paper, a comparative analysis of empresas publicas that cotizan in the Bolsa Mexicana de Valores (BMV) is presented.
Abstract: El objetivo de la presente investigacion es contribuir al conocimiento sobre el impacto que tienen los factores financieros y economicos en la insolvencia empresarial de las empresas publicas que cotizan en la Bolsa Mexicana de Valores (BMV) y se realiza un analisis comparativo entre empresas y sectores que han incurrido en insolvencia y las que no. Para ello se utiliza la metodologia de probit con datos panel. La informacion del presente estudio proviene de empresas publicas que han cotizado en la Bolsa Mexicana de Valores en los ultimos 26 anos. Los resultados indican que los factores financieros, no financieros y macroeconomicos son las determinantes en la insolvencia empresarial y por otra parte en el modelo multisectorial los sectores que tienen mas posibilidad de caer en la insolvencia empresarial son el sector de productos de consumo frecuente, el sector industrial, seguido por el sector de servicios y bienes de consumo no basico ya que el que menor riesgo tiene es el sector de materiales.
14 citations
TL;DR: This contribution focuses on the creation of a comprehensive method for the evaluation of an industrial enterprise, one that can be used to predict potential future bankruptcies, using a dataset of financial statements of active companies and those in liquidation in the period 2015–2019.
Abstract: For investment purposes, the evaluation of a company is not only a matter for a company itself, but also for shareholders and external persons. There are many methods for evaluating a company. This contribution therefore focuses on the creation of a comprehensive method for the evaluation of an industrial enterprise, one that can be used to predict potential future bankruptcies, using a dataset of financial statements of active companies and those in liquidation in the period 2015–2019. Artificial neural networks were used to process the data, specifically logistic regressions from the data processed in the Statistica and Mathematica software programmes. The results showed that the models created using the Mathematica software are not applicable in practice due to the parameters of the obtained results. In contrast, the artificial neural structures obtained using the neural network model in the Statistica software were prospective due to their performance, which is almost always above 0.8, and the logical economic interpretation of the relevant variables. All the generated and retained networks show excellent performance and few errors. However, one of the artificial structures, network no. 4 (MLP 16-16-2), produces better results than the others. Overall, accuracy is almost 81%. In the case of the classification of companies capable of surviving financial distress, accuracy is almost 90%, with that for the classification of companies at risk of going into bankruptcy at nearly 55%.
3 citations
TL;DR: In this paper , an Eagle Strategy Arithmetic Optimization Algorithm with Optimal Deep Convolutional Forest (ESAOA-ODCF) based FinTech Application for Hyperautomation was proposed.
Abstract: Hyper automation is the group of approaches and software companies utilised to automate manual procedures. Financial Technology (FinTech) was processed as a distinctive classification that highly inspects the financial technology sector from a broader group of functions for enterprises with utilise of Information Technology (IT) application. Financial crisis prediction (FCP) is the most essential FinTech technique, defining institutions’ financial status. This study proposes an Eagle Strategy Arithmetic Optimisation Algorithm with Optimal Deep Convolutional Forest (ESAOA-ODCF) based FinTech Application for Hyperautomation. The ESAOA-ODCF technique has achieved exceptional performance with maximum accu y of 98.61%, and F score of 98.59%. Extensive experimental research revealed that the ESAOA-ODCF model beat more modern, cutting-edge approaches in terms of overall performance.
2 citations
10 Jul 2019
TL;DR: In this paper, the authors define sposoby problematikou bankrotov podnikov and define a set of metodologies, including LASSO alebo PCA metodu.
Abstract: Predkladaný prispevok sa zaobera problematikou bankrotov podnikov a definuje sposoby akými je možne tomuto nežiaducemu stavu predisť. V sucasnosti medzi tieto sposoby patria hlavne moderne pristupy z oblasti ziskavania znalosti a dolovania v datach, ktore podnikom dokažu pomocť v mnohých smeroch. V ramci praktickej aplikacie metod dolovania v datach s cieľom predikovať buduci stav podniku, boli použite data financných ukazovateľov poľských spolocnosti. V predkladanom clanku sme využili algoritmy vhodne na predikciu bankrotov – rozhodovacie stromy, ktore poskytuju jednoduchu interpretaciu výsledkov. V niektorých experimentoch sme využili aj metody výberu atributov, LASSO alebo PCA metodu. Postup prace sa riadi metodologiou CRISP-DM, ktora ponuka popis doležitých krokov potrebných pri roznych analytických ulohach. Sucasťou clanku je aj analýza sucasneho stavu, ktora predstavuje riesenia danej problematiky inými autormi. Po vyhodnoteni vsetkých modelov sme dospeli k zaveru, že algoritmus C5.0 je na 97,07 % schopný predikovať zbankrotovanie respektive nezbankrotovanie podniku, pricom použitie metod výberu atributov nebolo potrebne.
1 citations
TL;DR: R HODE is the first system that provides the building blocks for the training of RNNs and its variants, under encryption in a federated learning setting, and it is proposed a novel packing scheme, multi-dimensional packing, for a better utilization of Single Instruction, Multiple Data operations under encryption.
Abstract: We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a cross-silo federated learning setting by relying on multiparty homomorphic encryption. RHODE preserves the confidentiality of the training data, the model, and the prediction data; and it mitigates federated learning attacks that target the gradients under a passive-adversary threat model. We propose a packing scheme, multi-dimensional packing, for a better utilization of Single Instruction, Multiple Data (SIMD) operations under encryption. With multi-dimensional packing, RHODE enables the efficient processing, in parallel, of a batch of samples. To avoid the exploding gradients problem, RHODE provides several clipping approximations for performing gradient clipping under encryption. We experimentally show that the model performance with RHODE remains similar to non-secure solutions both for homogeneous and heterogeneous data distribution among the data holders. Our experimental evaluation shows that RHODE scales linearly with the number of data holders and the number of timesteps, sub-linearly and sub-quadratically with the number of features and the number of hidden units of RNNs, respectively. To the best of our knowledge, RHODE is the first system that provides the building blocks for the training of RNNs and its variants, under encryption in a federated learning setting.
1 citations
References
More filters
01 Jan 2018
TL;DR: Melalui buku Analisis Kritis Laporan Keuangan inilah diharapkan dapat menjawab kebutuhan tersebut as discussed by the authors.
Abstract: Laporan keuangan merupakan media informasi yang merangkum semua aktivitas perusahaan bagi manajemen, investor, bank, pemerintah dan masyarakat umum. Karena itu penting sekali bagi para pelaku ekonomi dan mahasiswa Fakultas Ekonomi untuk menguasai konsep dan perkembangan teknik analisis laporan keuangan.
Melalui buku Analisis Kritis Laporan Keuangan inilah diharapkan dapat menjawab kebutuhan tersebut. Karena buku ini memberikan paparan yang rinci dan sistematis tentang analisis laporan keuangan disertai dengan contoh-contoh kasus dan latihan soal-soal agar bisa dibandingkan dengan teori-teori yang ada.
378 citations
TL;DR: Using neural networks as a learning paradigm, different techniques for choosing the inputs, outputs, and error function are described and the learning from hints technique that augments the standard learning from examples method is described.
Abstract: This paper provides a brief introduction to forecasting in financial markets with emphasis on commodity futures and foreign exchange. We describe the basic approaches to forecasting, and discuss the noisy nature of financial data. Using neural networks as a learning paradigm, we describe different techniques for choosing the inputs, outputs, and error function. We also describe the learning from hints technique that augments the standard learning from examples method. We demonstrate the use of hints in foreign-exchange trading of the U.S. Dollar versus the British Pound, the German Mark, the Japanese Yen, and the Swiss Franc, over a period of 32 months. The paper does not assume a background in financial markets.
341 citations
TL;DR: Experimental results on Korean firms indicated that the bagged and the boosted neural networks showed the improved performance over traditional neural networks on bankruptcy prediction tasks.
Abstract: In a bankruptcy prediction model, the accuracy is one of crucial performance measures due to its significant economic impact. Ensemble is one of widely used methods for improving the performance of classification and prediction models. Two popular ensemble methods, Bagging and Boosting, have been applied with great success to various machine learning problems using mostly decision trees as base classifiers. In this paper, we propose an ensemble with neural network for improving the performance of traditional neural networks on bankruptcy prediction tasks. Experimental results on Korean firms indicated that the bagged and the boosted neural networks showed the improved performance over traditional neural networks.
225 citations
01 Jan 2005
TL;DR: Model-model JST : Model sederhana seperti McCulloch-Pitts, hebb, hingga model-model ying umum dipakai seperi perceptron, adaline, madaline, back propagation, jaringan hamming, and kohonen as mentioned in this paper.
Abstract: Pokok bahasa buku ini antara lain:
Dasar-dasar JST: dasar-dasar matematika yangidbutuhkan, konsep dasar JST, komponen-komnponen JST, dll
Model-model JST : Model sederhana seperti McCulloch-Pitts, hebb, hingga model-model yang umum dipakai seperti perceptron, adaline, madaline, back propagation, jaringan hamming, dan kohonen.
Pemrograman JST: pengenalan dan konsep dasar matlab, pemrograman model-model JST dengan Matlab
185 citations