Çoklu Regresyon ve Yapay Sinir Ağları ile Tokat İlinde Konut Değerleme Çalışması

Tabar, Mehmet Emin; Başara, Aslan Cihat; Şişman, Yasemin

doi:10.51765/tayod.832227

Cited by 18 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study compared machine learning algorithms' performances to predict monthly housing sales in Konya. When examining the studies in the literature, there are differences in the estimation parameters and methods discussed [8,34,35,36]. In this study, within the framework of the existing literature, years, months, interest rates for housing loans, consumer price index, consumer confidence index, construction confidence index, dollar exchange rate, and industrial production index were determined as input parameters for the housing sales forecast in Konya.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Makine Öğrenmesi Yöntemleri ile Konut Talep Tahmini

Emeç

TEKİN

2022

Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi

View full text Add to dashboard Cite

Housing is a place where sustainable urban spaces are produced and where people's physical, cultural, environmental, economic, social and psychological needs are evaluated together with their surroundings, rather than just a building where the need for shelter is met. With the acceleration of urbanization, new needs arise, and the first of these is the need for housing. The housing sector has become one of the most dynamic and continuous sectors associated with the increase in the need for housing. The need for adequate and accessible housing comes to the forefront in our country as well as in the world. Understanding and predicting the key features determining housing prices and value is an important consideration for urban planners and housing policymakers. In this study, machine learning and artificial neural network models were used to predict the housing demand of Konya, and their forecasting performances were compared. As a result, it was concluded that ANN is a better alternative for housing demand forecasting in Konya.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Examples of advanced methods are Artificial Neural Networks (ANN), hedonic pricing, spatial analysis, fuzzy logic, etc. Examples of traditional valuation methods are the cost method, multiple regression method, and stepwise regression [7,8].…”

Section: Introductionmentioning

confidence: 99%

Makine Öğrenmesi Yöntemleri ile Konut Talep Tahmini

Emeç

TEKİN

2022

Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi

View full text Add to dashboard Cite

show abstract

“…Yaklaşık muhakeme gerektiren durumlarda bulanık mantık sistemleri daha uygundur. Geleneksel sistemlere kıyasla, bulanık mantık sistemleri daha hızlı yanıt verir ve kontrol sürecinde daha az karmaşıklık oluşur [25].…”

Section: Bulanık Mantık Yöntemiunclassified

“…Aynı zamanda, kural ve yüzey izleyicisi de bulunmaktadır. Sistem ve sistemin çalışmasının izlenmesine olanak tanır [30]. Bulanık mantık uygulama alanları Tablo 5'te sunulmuştur.…”

Section: Bulanık Mantık Yöntemiunclassified

Aegean Region fruit production assignment using Fuzzy Logic and ARAS methods

Akyer

2023

Pamukkale J Eng Sci

View full text Add to dashboard Cite

Türkiye'nin Ege Bölgesi iklim koşulları ve toprak özellikleri açısından meyve üretimine çok elverişli bir bölgedir. Ege Bölgesi'ndeki meyve ve sebze üretimi Türkiye tarım ekonomisi açısından önemli bir konuma sahiptir. Meyvecilik sektörü Türkiye'nin tarım ekonomisi açısından oldukça önemli bir yere sahiptir. Çalışmanın amacı, Ege Bölgesi'ndeki dengesiz meyve üretiminin önüne geçilerek daha verimli meyve yetiştiriciliğini sağlamaktır. Çalışmada, farklı koşullarda yetişen meyveleri Ege Bölgesi'ndeki farklı özelliklere sahip illerde dengeli bir şekilde üretiminin yapılacağı bir atama amaçlanmıştır. Atama problemi için Ege Bölgesi'ndeki şehirlerin koşulları ve meyvelerin yetişme koşulları birlikte ele alınmıştır. Bu koşullar; rakım, sıcaklık, toprak niteliği, iklim, nem, iş gücü ve sulamadır. Meyve üretimi için AHP yöntemiyle koşullar analiz edilmiş ve faktör ağırlıkları hesaplanmıştır. Meyvelerin atama problemini çözmek için ARAS ve Bulanık Mantık yöntemleri kullanılmıştır. Bu yöntemler, belli bir durumun hesaplanamayan özelliklerini sayısallaştırarak sonuca ulaşmayı sağlamaktadır. Endüstriyel değeri ve ihracat geliri yüksek olan başta incir, üzüm, kekik ve kiraz üretimi için sırasıyla Aydın, Manisa, Denizli ve Afyonkarahisar illeri önerilmiştir. Yapılan çalışma ülke genelinde her bölgede bu şekilde meyve ve sebze atamasının yapılarak dengesiz üretimin önüne geçilebileceğini göstermiştir. Sonuçta ülkenin tarım arazileri etkin kullanılabilecek ve tarımın milli ekonomiye katkısı artacaktır. Turkey's Aegean region is a very suitable region for fruit production in terms of climatic conditions and soil characteristics. Fruit and vegetable production in the Aegean region has an important position in terms ofTurkey's agricultural economy. The fruit growing sector has a very important place in Turkey's agricultural economy. The aim of the study is to prevent unbalanced fruit production in the Aegean region and to ensure more efficient fruit growing. In the study, it was aimed to assign a balanced production of fruits grown under different conditions in provinces with different characteristics in the Aegean region. For the assignment problem, the conditions of the cities in the Aegean region and the growing conditions of the fruits are considered together. These conditions are altitude, temperature, soil quality, climate, humidity, labor and irrigation. Conditions for fruit production were analyzed with the AHP method and factor weights were calculated. ARAS and Fuzzy Logic methods were used to solve the assignment problem of fruits. These methods enable to reach the result by digitizing the noncomputable features of a particular situation. Aydın, Manisa, Denizli and Afyonkarahisar provinces have been proposed, respectively, for the production of figs, grapes, thyme and cherries, which have high industrial value and export income. The study has shown that unbalanced production can be prevented by assigning fruits and vegetables in this way in every region of the country. As a result, the country's agricultural lands will be ...

show abstract

“…For value determination ANN and Multiple Regression were compared. ANN model accuracy is about the 96% and better than multiple regression [30].…”

mentioning

confidence: 92%

Housing Price Estimation with Deep Learning: A Case Study of Sakarya Turkey

OZDEMİR

Yildiz

BÜYÜKTANIR>

2022

Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

Shelter is one of the most basic human needs. Besides housing needs, the housing market is also very important for investment. It is also a market where many people, such as engineers, architects, real estate agents make economic gain. When a house is bought for living in it, it is not desired to be changed for many years, and when it is bought for investment, it is a tool that requires good income. Therefore, the best decision should be made when buying a house, and it should be scrutinized. Correct estimation of house prices is very important for both buyers to make the right decision and for sellers to sell without a loss. There are many parameters for estimating house prices. In addition to variables such as the number of floors, location, and several bathrooms used in previous studies, economic factors (such as the price of bread, foreign currency price, new car price) and the housing loan interest rate of the banks were taken as inputs in this study. Sakarya province, where all parameters can be tested to make a more accurate determination, was chosen as the research area. A comparison of polynomial regression, random forest, and deep learning methods was made and it was concluded that the most accurate method was deep learning. At the same time, it was determined which parameters are more effective in house price estimation.

show abstract

Çoklu Regresyon ve Yapay Sinir Ağları ile Tokat İlinde Konut Değerleme Çalışması

Cited by 18 publications

References 16 publications

Makine Öğrenmesi Yöntemleri ile Konut Talep Tahmini

Makine Öğrenmesi Yöntemleri ile Konut Talep Tahmini

Aegean Region fruit production assignment using Fuzzy Logic and ARAS methods

Housing Price Estimation with Deep Learning: A Case Study of Sakarya Turkey

Contact Info

Product

Resources

About