Scholarlink

<p>Price estimation remains as one of the most significant challenges enterprises face, specifically in the management consulting services domain, whereas numerous internal and external factors contribute in pricing. This study aims to address this issue in three steps with a combinational approach: (1) Identifying the main indicators that influence management consulting services pricing, (2) Applying regression analysis (3) Developing Artificial Neural Networks (ANN) models to predict the price highly accurately. Data collection strategies included structured interviews and surveys with a cross-sectional time-horizon and practical orientation. The ANN models were developed with MATLAB R2022a software. This study revealed 25 pricing influential factors, where top five identified with Minimum Redundancy Maximum Relevance (MRMR) algorithm are: the business size, the industry’s complexity level, the consultant’s contract type and academic background, and the project scope. The proposed classification ANN model achieved a 95.6% accuracy rate, where categorized the project prices into five categories (in 10^7 IRR): less than 100, 100–500, 500–1000, 1000–3000, and more than 3000.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing the price estimation in consulting services using empirically developed ANN

  • 期刊论文

  • 发表日期：

    2026年1月2日

查看全文
  • Ameneh Khadivar,
  • Payvand Mirzaeian Khamseh,
  • Raha Basraei,
  • Shib Sankar Sana

摘要

Price estimation remains as one of the most significant challenges enterprises face, specifically in the management consulting services domain, whereas numerous internal and external factors contribute in pricing. This study aims to address this issue in three steps with a combinational approach: (1) Identifying the main indicators that influence management consulting services pricing, (2) Applying regression analysis (3) Developing Artificial Neural Networks (ANN) models to predict the price highly accurately. Data collection strategies included structured interviews and surveys with a cross-sectional time-horizon and practical orientation. The ANN models were developed with MATLAB R2022a software. This study revealed 25 pricing influential factors, where top five identified with Minimum Redundancy Maximum Relevance (MRMR) algorithm are: the business size, the industry’s complexity level, the consultant’s contract type and academic background, and the project scope. The proposed classification ANN model achieved a 95.6% accuracy rate, where categorized the project prices into five categories (in 10^7 IRR): less than 100, 100–500, 500–1000, 1000–3000, and more than 3000.