# Big Data driven Product Design: A Survey

**Authors:** Huafeng Quan, Shaobo Li, Changchang Zeng, Hongjing Wei, Jianjun Hu  
**arXiv:** [2109.11424](https://arxiv.org/abs/2109.11424)  
**Date:** 2021-09-06  
**Summary page:** https://www.summarizepaper.com/en/paper/2109.11424v1/

## Key points

- Living standards are improving, leading to more personalized and diversified product design
- Traditional product design methods have limitations such as subjectivity, small survey scope, poor real-time data, and lack of visual display
- Big data-driven product design methodology is a promising solution
- Big data in the product lifecycle contains valuable information for guiding product design such as customer preferences, market demands, and product evaluation
- Online reviews reflect customer evaluations and requirements while product images contain information on shape, color, and texture that can inspire designers to generate new designs more quickly
- The study aims to conduct a comprehensive survey on big data-driven product design to help researchers and practitioners comprehend the latest developments in relevant studies and applications centered on how big data can be processed, analyzed, and exploited in aiding product design
- User experience feedback after purchasing the products is the most valuable for designers
- Online reviews from e-commerce websites are given by consumers who purchased them; hence they have high reliability and authenticity
- According to research conducted by experts in this field: 90% of customers take online reviews as a reference while 81% indicate it is helpful for purchase decisions
- The study highlights major deficiencies of existing data-driven product design studies while also providing future research directions that could lead to further development of modern data-driven product design methodologies that cater to diverse user requirements effectively.

## Summary

As living standards continue to improve, modern product design is becoming increasingly personalized and diversified. To address the limitations of traditional product design methods such as subjectivity, small survey scope, poor real-time data and lack of visual display, big data-driven product design methodology has emerged as a promising solution. Big data in the product lifecycle contains valuable information for guiding product design such as customer preferences, market demands and product evaluation. Online reviews reflect customer evaluations and requirements while product images contain information on shape, color and texture that can inspire designers to generate new designs more quickly. This paper aims to conduct a comprehensive survey on big data-driven product design to help researchers and practitioners comprehend the latest developments in relevant studies and applications centered on how big data can be processed, analyzed and exploited in aiding product design. The study first introduces several representative traditional product design methods and highlights their limitations before discussing current and potential applications of textual data, image data, audio data and video data in the product design cycle. The text exists in many phases of the product lifecycle with user experience feedback after purchasing the products being the most valuable for designers. More users have posted their opinions of products on social media platforms like Twitter or Facebook or e-commerce websites like Amazon or Alibaba in recent years. Online reviews from e-commerce websites are given by consumers who purchased them; hence they have high reliability and authenticity. According to research conducted by experts in this field: 90% of customers take online reviews as a reference while 81% indicate it is helpful for purchase decisions. In conclusion, this study highlights major deficiencies of existing data-driven product design studies while also providing future research directions that could lead to further development of modern data-driven product design methodologies that cater to diverse user requirements effectively.