fa توسعه یک سیستم تشخیص مشتری تلفیقی مبتنی بر درخت رگرسیونی هرس شده و شبکه عصبی بهبودیافته سایر موضوعاتی که به مرزهای دانش در مهندسی صنایع و تولید کمک می کند Other related Industrial and production reserach subjects in which has direct relation to the state-of-the art of the IE كاربردي Applicable <p align="right"><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt">در دنیای رقابتی امروزی، شیوه‌های جذب مشتری یکی از با اهمیت‌ترین حوزه‌های کاربردی داده‌کاوی بوده</span><span dir="ltr"></span><span lang="FA" style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US mso-bidi-font-size: 11.0pt"><span dir="ltr"></span> </span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt">و پرواضح است که یکی از مهمترین ابعاد آن پیش‌بینی رفتار خرید مشتری است. زیرا، پیش‌بینی خوب می‌تواند به توسعه استراتژیهای بازاریابی دقیقتر و صرف کاراتر منابع کمک نماید. ایجاد یک سیستم تشخیص مشتری</span><span dir="ltr"></span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US mso-bidi-font-size: 11.0pt"><span dir="ltr"></span>(</span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">CRS</span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US mso-bidi-font-size: 11.0pt">)</span><span dir="rtl"></span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt"><span dir="rtl"></span> به دلیل وجود تعداد زیادی ویژگی در دسترس طراح کاری بسیار مشکل است. بعلاوه، نیاز شدیدی به ایجاد یک </span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">CRS</span><span dir="rtl"></span><span dir="rtl" style="FONT-SIZE: 10pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US"><span dir="rtl"></span> </span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt">وجود دارد که همزمان پیچیدگی کم و قابلیت پیش‌بینی خوبی را داشته باشد. از اینرو، مقصود این مقاله، توسعه یک </span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">CRS</span><span dir="rtl"></span><span dir="rtl" style="FONT-SIZE: 10pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US"><span dir="rtl"></span> </span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt">تلفیقی </span><span dir="ltr"></span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US mso-bidi-font-size: 11.0pt"><span dir="ltr"></span>(</span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">HCRS</span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US mso-bidi-font-size: 11.0pt">)</span><span dir="rtl"></span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt"><span dir="rtl"></span> است که از نظر محاسباتی کارا و اثربخش است. نوآوری مدل </span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">HCRS</span><span dir="rtl"></span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt"><span dir="rtl"></span>، هم طراحی و هم پیاده‌سازی سیستم مذکور با ایجاد یک درخت رگرسیونی هرس شده </span><span dir="ltr"></span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US mso-bidi-font-size: 11.0pt"><span dir="ltr"></span>(</span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">PRT</span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US mso-bidi-font-size: 11.0pt">)</span><span dir="rtl"></span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt"><span dir="rtl"></span> و طراحی یک شبکه عصبی پیشخوراند بهبودیافته </span><span dir="ltr"></span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US mso-bidi-font-size: 11.0pt"><span dir="ltr"></span>(</span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">IFFNN</span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US mso-bidi-font-size: 11.0pt">)</span><span dir="rtl"></span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt"><span dir="rtl"></span> جهت افزایش سرعت، دقت و کاهش پیچیدگی را شامل می‌شود. از آنجاییکه، شناسایی مشتریان یکی از دغدغه‌های صنعت بیمه است، از داده‌های یک شرکت بیمه هلندی استفاده شده است. نتایج نشان داد که </span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">HCRS</span><span dir="rtl"></span><span dir="rtl" style="FONT-SIZE: 10pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US"><span dir="rtl"></span> </span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt">تنها 7% از ویژگی‌ها را در حالت بهینه انتخاب می‌کند که به میزان قابل‌توجهی هزینه محاسبات را کاهش می‌دهد. به‌‌علاوه، نتایج نشان داد که </span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">PRT</span><span dir="rtl"></span><span dir="rtl" style="FONT-SIZE: 10pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US"><span dir="rtl"></span> </span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt">نسبت به روش منحنی مشخصه عملیاتی دریافت‌کننده کاراتر بوده و </span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">IFFNN</span><span dir="rtl"></span><span dir="rtl" style="FONT-SIZE: 10pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US"><span dir="rtl"></span> </span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt">نسبت به </span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">FFNN</span><span dir="rtl"></span><span dir="rtl" style="FONT-SIZE: 10pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US"><span dir="rtl"></span> </span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt">و </span><span style="FONT-SIZE: 10pt FONT-FAMILY: "Times New Roman" mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-bidi-font-family: Nazanin mso-ansi-language: EN-US mso-fareast-language: EN-US">PRT</span><span dir="rtl"></span><span dir="rtl" style="FONT-SIZE: 10pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US"><span dir="rtl"></span> </span><span lang="FA" dir="rtl" style="FONT-SIZE: 11pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US mso-ansi-font-size: 10.0pt">پیش‌بینی‌های دقیقتری را ارائه می‌کند</span><span lang="FA" dir="rtl" style="FONT-SIZE: 10pt FONT-FAMILY: Nazanin mso-bidi-language: FA mso-fareast-font-family: 'Times New Roman' mso-ascii-font-family: 'Times New Roman' mso-hansi-font-family: 'Times New Roman' mso-ansi-language: EN-US mso-fareast-language: EN-US">.</span></p> <p> <i> In today’s world, customer purchasing behavior forecasting is one of the most important aspects of customer attraction. Good forecasting can help to develop marketing strategies more accurately and to spend resources more effectively. The creation of a customer recognition system (CRS) model concerns a difficult task due to the large number of possible features. Furthermore, there is a high need to create a CRS that have both low complexity and good forecasting abilities at the same time. Thus, the purpose of this paper is to develop a hybrid CRS (HCRS) model that is computationally efficient and effective. The novelty of the HCRS lies in the design and implementation of the mentioned system by combining a pruned regression tree (PRT) that increases computational speed to select suitable subset of features and designing an improved Feedforward neural network (IFFNN) that practically provides better forecasting results. Since customer identification is one of the concerns in insurance industry, an insurance company dataset has been used. The obtained results show that the HCRS selects just 7% of the available features in this way considerably reducing computation costs. In addition, the results show that making the IFFNN led to more accurate forecasting than the methods compared </i><i>. </i></p> انتخاب ویژگی، پیشبینی، درخت رگرسیونی هرس شده، سیستم تشخیص مشتری، شبکه عصبی بهبودیافته Feature Selection, Pruned Regression Tree, Customer Recognition System, Forecasting, Improved Neural Network 191 202 http://ijiepm.iust.ac.ir/browse.php?a_code=A-10-1-149&slc_lang=fa&sid=1 AliReza Soroush a.soroush@modares.ac.ir 180031947532846001816 180031947532846001816 No Ardeshir Bahreininejad bahreininejad@modares.ac.ir 180031947532846001817 180031947532846001817 Yes