Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-03 Cooperative journals: 《计算机应用研究》
Abstract： The traditional housing prices evaluation which was using Random Forest algorithm had a large number of parameter selection problems. The parameters had great influence on the accuracy of the algorithm. In order to solve this problem, this paper combined the Random Forest algorithm and simulated annealing algorithm and proposed a new algorithm about the housing prices evaluation. Firstly, according to the different sensitivity of the Random Forest parameters to the algorithm, this paper tested the sensitivity of the parameters by 10 times 10-cross-validation method, then selected the parameters of the algorithm. Secondly, this paper used the simulated annealing algorithm to the sensitive parameters iterative optimization. Through comparing to the grid search algorithm and random search algorithm, this paper found the simulated annealing algorithm do better than the grid search algorithm and random search algorithm in the running time and algorithm accuracy. The simulated annealing algorithm made up the defects of the time-consuming and the low-accuracy of the random search algorithm in the grid search when selecting parameters. At last, this paper applied the Random Forest algorithm combing with simulated annealing to the problem of housing prices evaluation, and formed a new evaluation algorithm. Comparing the new algorithm with the traditional Random Forest price estimation algorithm, the results show that the error value of the Random Forest price estimation algorithm with simulated annealing is reduced, the goodness of fit value increases, and the accuracy of the evaluation is improved markedly.
Hits
Hits
Downloads
Comment