Makine öğrenmesine dayalı talep tahmin modellerinin karşılaştırılması

Comparison of machine learning based demand forecasting models

PDF İndir

Tez No: 933153
Yazar: ERHAN KOR
Danışmanlar: PROF. DR. ORHAN TORKUL
Tez Türü: Yüksek Lisans
Konular: Endüstri ve Endüstri Mühendisliği, Industrial and Industrial Engineering
Anahtar Kelimeler: Belirtilmemiş.
Yıl: 2024
Dil: Türkçe
Üniversite: Sakarya Üniversitesi
Enstitü: Fen Bilimleri Enstitüsü
Ana Bilim Dalı: Endüstri Mühendisliği Ana Bilim Dalı
Bilim Dalı: Mühendislik Yönetimi Bilim Dalı
Sayfa Sayısı: 123

Özet

Üretim planlarındaki gecikmelerin önlenmesi için hammaddenin ve yarı mamulün belirlenen miktarda bulundurulması planların gerçekleşmesinde önemli bir etkiye sahiptir. Bu doğrultuda literatürde yapılan çalışmaların tedarik zincirinde sürekliliğin sağlanması ve müşteriye teslim tarihlerinin gerçeklenmesinde talep tahmin modellerinin önemi yadsınamaz. Literatürde ve endüstriyel raporlarda sipariş gecikmelerinin önlenmesi için gerekli çalışmalardan biri olan gerçekçi talep tahmin modellerinin geliştirilmesi önemli bir yer tutmaktadır. Bu çalışmada makine öğrenmesine dayalı gerçekçi bir talep tahmin modeli geliştirilmesi amaçlanmıştır. Bu çalışmayla ürünler için ihtiyaç duyulan sipariş gecikmelerinde birincil derecede önemli hammadde ve yarı mamulün ihtiyaç duyulan zamanda ve miktarda belirlenebilmesi bu problemleri önemli oranda azaltacaktır. Bu çalışmanın sonucunda aylık periyotta yapılan tahminler ile malzemelerin stok miktarlarının optimum seviyede bulundurulabilmesi sağlanacaktır. Sipariş fazlası ve ürün teslimatındaki gecikmelerin önemli oranda düşürülebileceği bu çalışmanın sonuçlarına dayanarak söylenebilir. Bu çalışmada geliştirilen modelin tahmindeki hataları azaltabileceği, son üç dönem talep ortalamalarının bağımsız değişkenler olarak ele alınması ile sağlanabileceği gözlemlenmiştir. Geliştirilen modelde enerji maliyeti, euro/dolar paritesi, çelik fiyatı, 1 ay önceki sipariş miktarı, 2 ay önceki sipariş miktarı, 3 ay önceki sipariş miktarı ve son 3 dönem sipariş ortalaması niteliklerinin yanı sıra talebin artması ve azaltılması trendlerinin belirlenmesinde çelik hammadde fiyatındaki değişim ile enerji maliyetlerindeki değişim ve sipariş miktarındaki değişimler de bağımsız nitelikler olarak ele alınmıştır. Tahmin modellerinin geliştirilmesinde yapay sinir ağları, karar ormanı ve lineer regresyon yöntemleri kullanılmış ve modellerin performansları değerlendirilerek karşılaştırılmıştır. Talep tahmin modellerinin geliştirilmesinde en ilgili özelliklerin belirlenebilmesi amacıyla Parçacık Sürüsü Optimizasyonu, Harris Şahini Optimizasyonu, Gri Kurt Optimizasyonu, Yusufçuk Optimizasyonu, Genetik Optimizasyonu ve Yerçekimi Arama Optimizasyonu olmak üzere 6 farklı nitelik seçimi yöntemi uygulanmıştır. Bu optimizasyon algoritmalarıyla nitelik seçimleri yapılarak daha doğru sonuç veren modeller geliştirilmiştir. Geliştirilen modellerde hammaddenin ve yarı mamullerin yeterli miktarda bulunmaması sipariş gecikmelerine, fazla olması ise stok maliyetlerinin artmasına neden olabilmektedir. Geliştirilmiş olan modelde tahmin hatalarının azaltılmasıyla sipariş gecikmelerinin ve stok maliyetlerinin azaltılabileceği öngörülmüştür. Modelin uygulanmasında kullanılan veriler çelik imalat sektöründe faaliyet gösteren büyük ölçekli bir firmadan temin edilmiştir. Modelin uygulanmasında dört farklı ürünün geçmiş yıllara ait satış verileri kullanılmıştır. 89 aylık veri toplanmış ve bunun 80 aylık verisi modeli eğitmek için, 9 aylık veri de test ve performans verisi olarak kullanılmıştır. Deneysel sonuçlara göre, nitelik seçimi yöntemlerinin genel olarak tahmin modellerinin performansını artırdığı sonucuna ulaşılmasına ragmen her bir ürün için en uygun tahmin performansını gösteren nitelik kümesi ve talep tahmini yöntemi kombinasyonunun farklılık gösterdiği değerlendirilmiştir. Geliştilen modeller sayesinde ürünler için sırasıyla %93,6, %94,7, %90,3 ve %91,5 tahmin doğruluğu değerine ulaşılmıştır. Geliştirilen modeller MAPE, MAE, RMSE ve MSE performans ölçütlerine göre değerlendirilmiş, yapay sinir ağları yöntemiyle geliştirilen modelin diğer modellere göre daha iyi sonuç verdiği değerlendirilmiştir. Yapay sinir ağlarıyla geliştirilen modellerin ortalama %91,9, karar ormanı yöntemi ile geliştirilen modellerin ortalama %91,3, lineer regresyon yöntemiyle geliştirilen modellerin ortalama %87,3 doğruluk değerine ulaştığı gözlemlenmiştir. Çalışmada önerilen metodolojinin çelik sektöründe faaliyet gösteren firmalar bünyesindeki ürünler için etkili bir şekilde kullanılabileceği öngörülmektedir.

Özet (Çeviri)

In order to prevent delays in production plans, keeping the raw materials and semi-finished products in the specified amount has a significant impact on the realization of the plans. In this regard, the importance of demand forecasting models in ensuring continuity in the supply chain and achieving customer delivery dates cannot be denied. Nowadays, as developments occur very rapidly and it becomes more and more difficult to keep up with developments, it has become a greater need for businesses to predict the future in order to maintain their existence. Being able to react to demands in a timely manner by adapting to changes in customer volumes and developments in technology contributes to the sustainability of the supply chain. It is possible for businesses to secure their future even in a highly competitive environment with a successful supply chain management. High variability in demand may cause disruptions in supply and inventory management. These disruptions may lead to increased costs due to excess stock or order losses as a result of products not being delivered. As a result of failure to control the disruptions, the situation may turn into customer loss for the business. Demand forecasting is one of the most needed functions in solving these problems. Demand forecasting methods offer advantages in many areas such as planning, cost and inventory management. With these advantages, companies' inadequacies decrease and their resilience in the market increases. The development of realistic demand forecast models, which is one of the necessary studies to prevent order delays, has an important place in the literature and industrial reports. In this study, it is aimed to develop a realistic demand forecasting model based on machine learning. With this study, determining the primary raw materials and semi-finished products at the required time and quantity in order delays needed for products will significantly reduce the problems. Despite the complex problems involved in demand forecasting processes, the common goal in demand forecasting is to benefit businesses by making a future forecast with high accuracy. At the same time, thanks to accurate forecasts, the efficiency of businesses increases. More accurate determination of product quantity and variety places demand forecasting at the center of planning. Compared to traditional forecasting methods, machine learning-based forecasting methods provide better results. In this study, which was conducted using real sales data through a case study, solutions were realized with selected machine learning-based methods. It is aimed to determine the method that gives the optimum result with the established models. The data to be used in demand forecast models were selected among the parameters that directly or indirectly affect the demands of products whose main component is steel. Euro/dollar parity was chosen as one of the independent variables, because the raw materials used in the production of the products are traded internationally in dollars and sales are made in euros. Since approximately 80% of the cost of the products comes from raw materials and the main component of the products is steel, the price of steel has become another independent variable. Energy cost was used as another independent variable, as the most important cost item in the cost of the products after the raw material and machinery investment cost. Additionally, there was a need to add recent data to increase the accuracy of the demand forecast model. Thus, in the models, actual order data for each product one, two and three months ago was also evaluated among the independent variables. The actual sales data used in the demand forecast model was taken from a large-scale international company selling products in the steel industry. In addition to the data of the last three periods, the attribute was created with the moving average data of the last three months. In the re-model simulations, it was observed that the addition of these features significantly contributed to the reduction of errors. In addition, it was realized from the simulations that the change in variables should be included among the attributes in order for the model to follow the changes in orders. In this regard, the differences in steel prices between periods, the differences in energy costs between periods and the change values of orders between periods were added to the independent variables. When deciding to use independent variables in the models, various modeling simulations were made with the available data. Comparisons of artificial neural networks, decision forest and linear regression methods were made to evaluate the performance of the demand forecasting model. Statistical methods have been applied to the independent components used in artificial neural networks, decision forest and linear regression models to obtain more accurate results in the models. In the training set, changes such as replacing the distribution of the data that disrupted the series and were at the extreme ends of the distribution with the average value, normalization, and logarithmic transformations were made. Outlier data in the data set used in the model were replaced with average values. While the values at the extremes were removed, the values above 95% and below 5% were selected. In addition, since the range of real sales values used in training the model was very wide, logarithmic transformation was performed to eliminate the skewed distribution in the data and obtain a distribution close to the normal distribution. In order to determine the most relevant features in the development of demand forecast models, 6 different feature selection methods were applied: Particle Swarm Optimization, Harris Hawk Optimization, Grey Wolf Optimization, Dragonfly Optimization, Genetic Optimization and Gravity Search Optimization. By making feature selections with these optimization algorithms, models that give more accurate results have been developed. In the developed models, not enough raw materials and semi-finished products may cause order delays, while their excess may cause an increase in stock costs. In the developed model, it is predicted that order delays and inventory costs can be reduced by reducing forecast errors. As a result of this study, it will be ensured that the stock quantities of the materials are kept at the optimum level. Based on the results of this study, it can be said that overorders and delays in product delivery can be significantly reduced. Considering all the findings in the literature, in this study, experiments were conducted with data splitting rates of 70-30%, 80-20% and 90-10% in training the models. Test studies have shown that the best results are achieved with the 90-10% option. It is predicted that the reason for this difference from the 80-20% rate found in the majority of the literature is that the number of periods of available data is relatively less. 89 months of data were collected, 80 months of which were used to train the model, and 9 months of data were used as test and performance data. The models developed within the scope of this study were compared according to different demand forecasting methods. In this study, 84 (4x3x7) different models were developed for 4 different products selected for welded steel manufacturing products, 3 different machine learning algorithms and 7 cases with and without feature selection, and these models were evaluated in terms of performance criteria. When the developed models were evaluated according to MAPE, MAE, RMSE and MSE performance criteria, it was evaluated that the model developed with the artificial neural networks method gave better results than other models. Four models built with the artificial neural networks method made predictions with high accuracy. With the decision forest method, highly accurate forecast was obtained in 3 models and good forecast was obtained in 1 model. Among the models created with the linear regression method, highly accurate forecast was obtained in 1 model and good forecast values were obtained in 3 models. It was observed that the model developed with artificial neural networks reached an average accuracy of 91.9%, the model developed with the decision forest method reached 91.3%, and the model developed with the linear regression method reached 87.3% accuracy. The artificial neural networks method predicted the highest and lowest demands better than other methods. It is predicted that if the artificial neural networks method is used in other demand forecasting studies, as in this study, it will achieve the objectives of the research by providing highly accurate forecasts. If the decision forest method is used, generally highly accurate forecasts can be obtained, as in artificial neural networks. It can be said that the the forecasts obtained with decision forests will similarly provide the desired benefits to the business at a slightly lower level than the artificial neural networks method. It can be predicted that the linear regression model can provide good forecasts, but when error rates are encountered, it does not need to be preferred over other methods. As a result, it has been observed that the artificial neural network model is a more accurate choice for the desired contributions.

Benzer Tezler

Tez No
726855
Dağıtık üretim sistemlerinin akıllı şebekeler üzerine etkilerinin incelenmesi
Examination of the effects of distributed generation on smart grids
MİKAİL PÜRLÜ
Doktora
Türkçe
2022
Elektrik ve Elektronik Mühendisliği İstanbul Teknik Üniversitesi
Elektrik Mühendisliği Ana Bilim Dalı
PROF. DR. BELGİN TÜRKAY
Tez No
768774
Development of a machine learning prediction model for construction safety management
İnşaat iş güvenliği yönetimi için makine öğrenmesine dayalı tahmin modeli geliştirilmesi
KERİM KOÇ
Doktora
İngilizce
2022
İnşaat Mühendisliği Yıldız Teknik Üniversitesi
İnşaat Mühendisliği Ana Bilim Dalı
DOÇ. DR. ASLI PELİN GÜRGÜN
Tez No
743485
Makine öğrenmesi yöntemleri kullanılarak market satış tahmin modellerinin oluşturulması
Creating demand forecasting models using machine learning methods
SİNEM SEÇGİN OLGUN
Yüksek Lisans
Türkçe
2022
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol Kocaeli Üniversitesi
Bilişim Sistemleri Mühendisliği Ana Bilim Dalı
DOÇ. DR. HİKMET HAKAN GÜREL
Tez No
563793
Customer churn analysis based on machine learning by using data mining techniques in telecommunication sector
Telekomünikasyon sektöründe veri madencilik tekniklerini kullanarak makine öğrenmesine dayalı müşteri terk analizi
ELİF ÇELİK
Yüksek Lisans
İngilizce
2019
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol Yeditepe Üniversitesi
Yönetim Bilişim Sistemleri Ana Bilim Dalı
DOÇ. DR. AŞKIN DEMİRAĞ
Tez No
888598
PLC kontrollü makinalarda, IoT cihazları kullanarak OPC-da tabanlı web servis ve yapay zeka geliştirilerek kestirimci bakım uygulaması
Predictive maintenance application by developing OPC da based web service and artificial intelligence using IoT devices on PLC controlled machines
AYHAN ÖZTÜRK
Yüksek Lisans
Türkçe
2024
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol Yıldız Teknik Üniversitesi
Kontrol ve Otomasyon Mühendisliği Ana Bilim Dalı
DR. ONUR AKBATI

Geri Dön