decision tree algorithm

Land is the basis of most human activities, production systems, and achieving sustainable development. On the other hand, with social and economic changes and unconventional resource exploitation, land instability conditions are intensifying. Measuring land use changes requires examining issues such as land use system, land cover, and monitoring patterns. Land use and land cover patterns, by providing monitoring and understanding the process of changes in the exploitation system through the use of remote sensing techniques, facilitate the possibility of reforming and changing policymaking, optimal management, and future planning of environmental resources. The aim of the present study is to monitor the changes in the LULC system in the Kuhpayeh-Segzi sub-basin using satellite images in the period 2000 to 2023 and update spatial information. The results of the evaluation of the land use and land cover maps using the Decision Tree Algorithm indicate an increase in the area of ​​more than 97% of built-up land, 173% of rangeland, 230% of irrigated areas, 72% of agricultural land, and a decrease in the area of ​​more than 14% of barren land. In this process, 913 hectares of barren land, 244 hectares of rangeland, 44 hectares of agricultural land, and 0.155 hectares of irrigated areas have been converted into built-up land. Sustainability of environmental resources, especially reducing the trend of land use and land cover change and stabilizing the exploitation system, requires the implementation of optimal resource management and the application of land protection models with the participation and empowerment of local rural communities.

Tax revenues are one of the most important sources of government income and provide a major part of its expenses. The main goal of this research is which of the decision tree algorithm and linear multivariate regression methods provides a better prediction of tax evasion of legal taxpayers. Based on the theoretical foundations and background studies of a set of variables including 57 financial and non-financial indicators at three macroeconomic levels, taxpayers and tax auditors, in a sample consisting of 964 cases of legal entities at the level of the Mazandaran General Administration of Tax Affairs for the years 2012 to 2019 with The use of Python and Stata software has been investigated. At first, the sine-cosine identification algorithm was used to select the influencing variables. The results of the data analysis showed that the variables at the level of taxpayers and tax auditors are more effective in predicting tax evasion. Also, the findings indicate that the predictive power of the decision tree algorithm is higher than the linear multivariate regression

The quality of audit institutions is always one of the most important things in auditing. Researchers in this field believe that the most effective variable in the discussion of audit quality is audit institutions .The purpose of this study is to present a new method for predicting and ranking the quality of audit institutions affiliated to Iranian Institute of Certified Public Accountants (IACPA). and its innovation is to achieve a highly accurate forecasting model. For this purpose ,we used data records of the quality control and status control of IACPA which had already been gathered through questionnaires from 2012 to 2017. We selected 1555 pieces of information records. After screening and deleting incomplete data, 1367 pieces of information were studied. Then, to reduce the data dimensions and find the internal and optimal pattern of variables set. Factor analysis and structural equation techniques were applied. The analysis revealed three categories paly ing a major role in quality of audit. These categories, constructs, were labelled process indicators , environmental or contextual indicators and input indicators. Finally, we used decision tree algorithm from data mining techniques, namely, C&R, and C5.0 algorithms. The results showed that C5.0 algorithm with 92% accuracy and sensitivity, and 97% detection power is the best performance for predicting audit quality and The C&R algorithm is able to predict the qualitative ranking of auditing institutions with 83% accuracy and sensitivity and 93% detection power

Players are the most important and valuable assets of sports clubs; their contracts cover most of the clubs' budgets. The present study aimed to investigate the role of those factors related to players’ valuation and predict the amount of their contract. The research method was applied-survey and quantitative; the research sample were selected by census sampling method including 41 players of the Esteghlal Club football team. The data from the research were based on the text mining method of the players' performance data for two seasons. When applying data mining method, neural network algorithms, decision tree and average chi-square clustering algorithm were used for data categorization, data analysis and price prediction. Also, the obtained model was tested by predicting the price again with the data using algorithms made in different models and applying graphs and numerical analysis and the predicted value with the actual value in the Clementine software. According to the results, dive had the highest impact factor and total time played during a season had the lowest impact factor for players’ valuation in the neural network algorithm. Age was the factor with the highest effect on players’ price, and players’ position was had the lowest effect in the decision tree algorithm. Physical activity was also the first factor affecting the price. The difference between predicted values in algorithmic methods and the actual data is probably due to the lack of a scientific approach to determine the value of players' contracts. Decision tree algorithm is recommended when predicting players' prices with the club fixed budget and the neural network is the most appropriate method when the budget is varied.

Financial and economic decisions are always at risk due to future uncertainties. Therefore, one of the ways to help investors is to provide investment risk forecasting patterns. The more predictions are closer to reality, the decisions made on the basis of such predictions will be correct. In this research, the goal of predicting the systematic risk of companies admitted to Tehran Stock Exchange using artificial neural network software and three night-worm algorithms, decision tree algorithm and backup vector machine regression algorithm. For this research, a sample of 92 companies from listed companies in Tehran Stock Exchange during the period 2013 to 2018 has been used. The results obtained from the research hypothesis test showed that the predictive power of systematic risk in the night cream algorithm is more than the decision tree algorithm and the support vector machine regression algorithm, as well as the predictive power of the decision tree algorithm in relation to the backup vector machine regression algorithm It is higher for systematic risk prediction

The purpose of this paper is to predict the quality of the audit using decision tree algorithms. Therefore, all audit institutions of the member of the Iranian Society of Official Accountants during the period 1391 to 1396 are the statistical population of the study, which after the screening of 1367 observations remained as a statistical sample. This research is a descriptive-correlative research in terms of applied and descriptive research method. Data analysis was performed in accordance with the CRISP-DM data mining standard and the implementation of four decision tree CHAID, C & RT, C5.0, and QUEST algorithms. Decision trees were modeled using simulation software of IBM modeler18 and the results showed that the optimal models, regardless of tree depth, with the maximum recognition power associated with the tree C5.0 over 97% and considering the depth of the tree with more than 92% is related to the C & RT tree. From the total of 19 quality assessment criteria, 16 criteria in the C5.0.12 Criterion Algorithm in the CHAID algorithm and 5 C & RT criteria and 3 criteria in QUEST are considered in the prediction of effective audit quality It is important to note that the common criteria in all four algorithms, which are employee recruitment, employee training, and entrepreneurship All work control and supervision are all input phases that affect audit quality.

Extended Abstract Introduction The relationship between form and process in geomorphology is very important. By changing the process, the forms will be changed and new processes will be created in the form of new forms (Gurabi & Emami, 2017. p:75). Sea level changes mainly include tidal variations and changes due to atmospheric factors. Tidal flows are also affected by coastal washing during their daily advancement and retreat on tidal slopes and tidal zones. The formation of many coastal geomorphologic forms is the result of their involvement. (Nohegar & Hosseinzadeh, 2011. P:131). Climatic factors cause short time fluctuations and tidal cycles and long term fluctuations in medium level of sea (Yamani & MohammadNejad, 2012: p: 87). Torabi Azad and Honarmand (2016) performed a concise investigation about sea level changes in Banda Abbas and Booshehr Stations in a period of 11 years (2000 to 2010) and analyzed and computed barometric effects, wind force and temperature on the sea level mean. The results showed that sea level mean in these stations has incremental trend by 5 cm and 4 cm respectively in the mentioned seaports. Akbari et al (2017) In order to investigate and analyze important tidal components in a vast area including Persian Gulf, Hormuz Strait, Oman sea and Arab sea applied 3D FVCOM Model. The results of this research shows that there is four kinds of tides in Persian Gulf including Daily, semi-Daily, daily compounded and semi-daily compounded tides and on the other regions there is just semi-daily compounded ides.The research aims on investigating the effects of climate change parameters (temperature, pressure, and wind rate) on the sea level fluctuations in an annual, seasonal and monthly changes and 20-year period in northern coasts of Oman Sea and also its physical justifications. Matarials and methods Research domain from geographical networking point of view, Jask port has longitude and latitude of 570 46' in east and 250 40' in north respectively to Gowatre Bay and in the terminal point of southeast of Iran and southwest of Pakistan has longitude and latitude of 570 46' in east and 250 10' in north respectively. Through calculating mean sea level from tide gauges datum belonged to IOC (Intergovernmental Oceanographic Commission) in the stations of hydrography of Jask and Chabhar ports during 1997 to 2016. Tide gauges for mentioned stations during 24 hours presented 1440 datum. In fact they registered sea level in every minutes. Data presented in every minute through averaging changed firstly into hourly data then into daily and finally into monthly data. In order to compute data based on monthly averages, the tidal effect should be deleted and computed into level fragment that means sea level minus tidal effect. According to the presented information in meteorological organization since 1997 to 2016, data about pressure, temperature and wind force were used in research stations as monthly means and the diagrams used monthly, seasonal and yearly means. In this research, Meta heurestic-Algorithm (Decision Tree Algorithm) The CARD regression tree decomposition algorithm (Classification and regression tree) is used as a type of regression decision tree for prediction purposes. Different elements have been used in simulation using decision tree model. In order to verify the relationship between the final decision tree tree based on the statistical index, graphical graphs and correlation coefficients obtained from the field operation method, visual inspection, ground monitoring and verification of control points were made. Result and discussion . The decision tree model in the Jask area has three parameters: wind pressure and wind speed, and the tree has acted on the basis of these two parameters that the model did not use the temperature parameter in the decision tree and was not selected as an effective parameter Is. Also in Chabahar region, all three parameters are used in the model The above-mentioned model has a very high performance in predicting values. In most of the 12-month intervals, the model performed its predictions close to real values; in other words, the tree created using data has a good prediction process and can simulate the changes well Also, according to the above figure, the predictions were evaluated. The results indicate that this model can be predicted with high accuracy and 95% confidence level in the region data. Because the temperature parameter has not been able to predict the response variable in the decision tree, the model has been eliminated, and the final equation of Jask and Chabahar is as follows. MSL(Jask) =13.197+5.619 T(1.102)-11.092 P (0.195)+7.208 W(0.71) MSL(Chabahar)= 4.520+1.529 T (1.089)-1.596 P(0.87)+2.776 W(0.316) Conclusion MSL fluctuations are among the general methods of analysis; therefore, accurate prediction can provide conditions for assessing its status. The purpose of this study was to investigate the effect of data pre-processing on the performance of nonlinear decision tree model in predicting MSL in Jask and Chabahar.The results of this study in all simulations show that pressure and wind parameters are more effective in the final model, which indicates the importance of these parameters in predicting future MSL. Physically, the close relationship between wind speed and water level changes is evident with the strong positive correlation coefficient of the Jask station compared to the Chabahar station in the annual windfall of both regions. Based on the relationship between the final model derived from the decision tree tree algorithm in MSL prediction using available data, it is 95% reliable. Investigating the related geomorphologic forms in the study area, the tidal range fluctuations in the Chabahar region are 1 to 1.5 meters, and in the Jask area more than 3 meters above the time interval are shown well in the diagrams. Therefore, in a closer examination of the processes governing the environments around the coastline, studying and monitoring the status of the tidal region and the influential climatic parameters is necessary.

Inventories constitute the main part of firms’ working capital. Maximizing the return from inventory holding is one of the financial managers’ goals and to achieve this purpose, an optimal level of inventory holding must be identified by manager and this requires the identification of factors affecting firms’ inventory holding. In this research, first the determinants of inventory holding are identified using multivariate regression analysis in 158 firms from 2002 to the end of 2013 and then the importance of significant factors is ranked using decision tree and neural network algorithms. The results of regression analysis show that except firms’ leverage and age, other research variables show a significant relationship with the level of inventory holding. Also, the ranking process of variables indicate that capital expenditure and firm size posit the most importance and cash from operations and firm growth have the least importance in explaining the level of firms’ inventory holding.

The purpose of this paper is to develop a model for prediction of present and prospect stock return using financial ratios. For this purpose, decision tree method was used. In this approach, a set of logical conditions in a hierarchical algorithmic model have been used for prediction or recognition of an event. Hereupon in this research, 70 percent of data were used to produce models in four popular decision tree algorithms (CHAID, ECHAID, QUEST and CRT) and the results of the tests were compared in 30 percent of residual of data with some of performance measures like accuracy, sensitivity and specificity. Information of 317 companies accepted in Tehran Stock Exchange was used in this study. The results indicated that ECHAID and CRT algorithms performed best in the prediction of present and CHAID algorithm in that of future. It was also shown that the models were better in that of present compared to that of future. The abilities of the models, however, were not significant in both cases. Accordingly, the hypothesis of the study was rejected.