Application of Metasynthesis in Identifying New Combined Genetic Algorithm Methods to Solve Problems in Oil Price Forecasting
محل انتشار: فصلنامه مطالعات پردازش دانش، دوره: 4، شماره: 3
سال انتشار: 1403
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 42
فایل این مقاله در 14 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_IJKPS-4-3_004
تاریخ نمایه سازی: 16 تیر 1403
چکیده مقاله:
The current research seeks to identify new combined genetic algorithm methods to solve price forecasting It was oil.Effective factors were identified by using a systematic and meta-composite review approach, and performing the ۷ steps of the Sandelowski and Barroso method. Among ۴۳۴۰ articles, ۵۴ articles were selected based on the CASP method. In this context, in order to measure reliability and quality control, the Kappa index was used, and its value was identified for the identified indicators at the level of excellent agreement.The results of the data analysis collected in the ATLAS TI software led to the identification of ۷ categories and ۲۶ primary codes of new combined genetic algorithm methods to solve completely difficult problems. Based on the done coding, ۷ categories and ۲۶ primary codes were identified. The identified categories are: component design, supply network, planning, forecasting, inventory control, information security, segregation and evaluation.The combination of genetic algorithm with different methods due to its ability to distinguish features and optimize parameters can lead to significant improvements in the field of oil price prediction. The use of genetic algorithm in solving oil price forecasting problems as an evolutionary and artificial intelligence approach makes it possible to integrate diverse and complex information in forecasting models. By designing the appropriate components as genes that represent important economic, geographic and political features, the most optimal genetic combinations can be created to increase the accuracy and performance of prediction models.
کلیدواژه ها:
نویسندگان
Alireza Daghighiasli
Department of Economics, Central Tehran Branch, Islamic Azad university, Tehran,
Atefeh Heidari
Department of Economics, Central Tehran Branch, Islamic Azad university, Tehran, Iran
Ebrahim Abbassi
Department of Economics, Central Tehran Branch, Islamic Azad university, Tehran, Iran
Marjan Damankeshideh
Department of Economics, Central Tehran Branch, Islamic Azad university, Tehran, Iran
مراجع و منابع این مقاله:
لیست زیر مراجع و منابع استفاده شده در این مقاله را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود مقاله لینک شده اند :