Abstract Nowadays, the softwarization and virtualization of resources and services rapidly continue, and along with reading and writing, programming is going to be one of the basic human ability. Thus, the detection of skilled programmers at an early age has become important for economies to strengthen their workforce and compete globally. The current technological momentum shows that when the middle school students of today reach the 2030s, the demand for advanced programming skills will be rapidly increased, expanding as high as 90% between 2016 and 2030. Thus, the identification of these skilled people at an early age is important. Accordingly, this study focused on predicting middle school students’ programming aptitude using artificial neural network (ANN) algorithms. A participant survey was developed and applied to middle school students consisting of fifth, sixth, and seventh graders from Konya Science Center, Turkey. After the completion of the survey, the participants then took the 20-level Classic Maze course (CMC) on Code.org. The participants’ final scores in the CMC were calculated based on the level they completed and the lines of codes they wrote. The best results were obtained using the Bayesian regularization algorithm: Training-R = 9.72284e−1; Test-R = 9.12687e−1, and All-R = 9.597e−1. The results show that ANN is an appropriate machine learning method that can forecast participants’ skills, such as analytical thinking, problem-solving, and programming aptitude.

中文翻译：

---

基于人工神经网络的中学生编程天赋预测

摘要 如今，资源和服务的软件化和虚拟化迅速发展，随着阅读和写作，编程将成为人类的基本能力之一。因此，在早期发现熟练的程序员对于经济体加强劳动力和全球竞争变得很重要。目前的科技发展势头表明，当今天的中学生到 2030 年代时，对高级编程技能的需求将迅速增加，在 2016 年至 2030 年间增长高达 90%。因此，尽早识别这些技能人员年龄很重要。因此，本研究侧重于使用人工神经网络 (ANN) 算法预测中学生的编程能力。对来自土耳其科尼亚科学中心的五年级、六年级和七年级学生进行了一项参与者调查并对其进行了调查。完成调查后，参与者随后参加了 Code.org 上的 20 级经典迷宫课程 (CMC)。参与者在 CMC 中的最终分数是根据他们完成的级别和他们编写的代码行数计算的。最好的结果是使用贝叶斯正则化算法获得的：Training-R = 9.72284e-1；测试-R = 9.12687e-1，并且所有-R = 9.597e-1。结果表明，人工神经网络是一种合适的机器学习方法，可以预测参与者的技能，如分析思维、解决问题和编程能力。然后，参与者参加了 Code.org 上的 20 级经典迷宫课程 (CMC)。参与者在 CMC 中的最终分数是根据他们完成的级别和他们编写的代码行数计算的。最好的结果是使用贝叶斯正则化算法获得的：Training-R = 9.72284e-1；测试-R = 9.12687e-1，并且所有-R = 9.597e-1。结果表明，人工神经网络是一种合适的机器学习方法，可以预测参与者的技能，如分析思维、解决问题和编程能力。然后，参与者参加了 Code.org 上的 20 级经典迷宫课程 (CMC)。参与者在 CMC 中的最终分数是根据他们完成的级别和他们编写的代码行数计算的。最好的结果是使用贝叶斯正则化算法获得的：Training-R = 9.72284e-1；测试-R = 9.12687e-1，并且所有-R = 9.597e-1。结果表明，人工神经网络是一种合适的机器学习方法，可以预测参与者的技能，如分析思维、解决问题和编程能力。