基于自适应学习的地块定价策略研究

基于最小二乘法的自适应地块价值评估策略,本文将机器学习模型与专家经验提炼的逻辑框架相结合,通过机器学习去全量化、自动化学习框架参数可以有效提高定价精度,改进后的定价系统可以达到商用级别精度(90％以上),较专家定价,具有成本低、效率高、精度强的优点,较纯机器学习模型定价,高质量样本量的需求大幅减少,达到低成本、高效率、...

Improved Land Pricing Strategy Based on Self-adaptive Learning

In this paper,the adaptive residential land pricee evaluation strategy is proposed.It is based on the least square method combines the machine learning model with the logical framework refined by expert experience.The pricing accuracy can be effectively improved by fully automatically quantifying the parameters of the strategy framework through machine learning,The improved pricing system can achieve commercial level accuracy(more than 90%),and has the advantages of low cost,high efficiency and strong accuracy compared with expert pricing.Compared with pure machine learning model pricing,the demand for high-quality sample size is greatly reduced,so as to achieve the effect of automatic land pricing with low cost,high efficiency and high accuracy.