In online teaching situations, a decision tree (DT) analysis algorithm is proposed in order to enable teachers to track students' learning behaviors and learning status in a timely manner. With the help of this algorithm, teachers can use the existing learning record files to analyze students' learning behaviors through multiple observation dimensions. In this paper, by constructing a learning achievement classification prediction (CP) model based on ID3 decision tree algorithm (DTA), the optimized ID3 DTA is used to analyze students' learning achievement and predict students who may not reach the expected teaching goals, so that teachers can give appropriate teaching assistance in time to achieve teaching goals. Through experiments, it is proved that with the increase of data volume, the accuracy of the model for CP of learning achievement is stable above 80%, which realizes the function of ID3 algorithm achievement prediction.

Jiwei Zhang. Application and Optimization of Decision Tree Algorithm in Classification Prediction. Machine Learning Theory and Practice (2021), Vol. 2, Issue 4: 18-25. https://doi.org/10.38007/ML.2021.020403.

[1] Alejandro Barredo Arrieta, Sergio Gil-Lopez, lbai Lata, Miren Nekane Bilbao, Javier Del Ser: On the post-hoc explainability of deep echo state networks for time series forecasting, image and video classification. Neural Comput. Appl. 34(13):10257-10277 (2021). https://doi.org/10.1007/s00521-021-06359-y

[2] Everton Castelao Tetila, Bruno Brandoli Machado, Jose F. Rorigues Jr, Diego A. Zanoni, Nicolas Alessandro de Souza Belete, Thayliny Zardo, Michel Constantino, Hemerson Pistori: Associative classification model for forecasting stock market trends. Int. J. Bus. Intell. Data Min. 19(1): 97-112 (2021). https://doi.org/10.1504/IJBIDM.2021.115968

[3] Mohammad Masdari, Afsane Khoshnevis: A survey and classification of the workload forecasting methods in cloud computing. Clust. Comput. 23(4): 2399-2424 (2020). https://doi.org/10.1007/s10586-019-03010-3

[4] Joy Dhar, Asoke Kumar Jodder: An Effective Recommendation System to Forecast the Best Educational Program Using Machine Learning Classification Algorithms. Ingenierie des Systemes d Inf. 25(5):559-568 (2020). https://doi.org/10.18280/isi.250502

[5] Asmaa H. Rabie, Shereen H. Ali, Ahmed 1. Saleh, Hesham A. Ali: A fog based load forecasting strategy based on multi-ensemble classification for smart grids. J. Ambient Intell. Humaniz. Comput. 11(1): 209-236 (2020). https://doi.org/10.1007/s12652-019-01299-x

[6] Ranjeeta Bisoi, P. K. Dash, Pragyan P. Das: Short-term electricity price forecasting and classification in smart grids using optimized multikernel extreme learning machine. Neural Comput. Appl. 32(5): 1457-1480 (2020). https://doi.org/10.1007/s00521-018-3652-5

[7] Mohamed Amgad, Lamees A. Atteya, Hagar Hussein, Kareem Hosny Mohammed, Ehab Hafiz , Maha A. T. EIsebaie, Pooya Mobadersany, David Manthey, David A. Gutman, Habiba Elfandy, Lee A. D. Cooper: Explainable nucleus classification using DT Approximation of Learned Embeddings. Bioinform. 38(2): 513-519 (2021). https://doi.org/10.1093/bioinformatics/btab670

[8] Pravin S. Game, Vinod Vaze, Emmanuel M: Optimized DT rules using divergence based grey wolf optimization for big data classification in health care. Evol. Intell. 15(2): 971-987 (2021).

[9] Chandrashekhar Azad, Bharat Bhushan, Rohit Sharma, Achyut Shankar, Krishna Kant Singh, Aditya Khamparia: Prediction model using SMOTE, genetic algorithm and DT (PMSGD) for classification of diabetes mellitus. Multim. Syst. 28(4): 1289-1307 (2021). https://doi.org/10.1007/s00530-021-00817-2

[10] Mohebbanaaz, L. V. Rajani Kumari, Y. Padma Sai: Classification of ECG beats using optimized DT and adaptive boosted optimized DT. Signal Image Video Process. 16(3): 695-703 (2021). https://doi.org/10.1007/s11760-021-02009-x

[11] Pietro Ducange, Francesco Marcelloni, Riccardo Pecori: Fuzzy Hoeffding DT for Data Stream Classification. Int. J. Comput. Intell. Syst. 14(1): 946-964 (2021). https://doi.org/10.2991/ijcis.d.210212.001

[12] Hong Nguyen Thi Khanh: Classification of Concepts Using DTs for Inconsistent Knowledge Systems Based on Bisimulation. J. Inf. Hiding Multim. Signal Process. 12(1): 22-30 (2021).

[13] Vinay Arora, Rohan Singh Leekha, Inderveer Chana: An Efficacy of Spectral Features with Boosted DTA for Automatic Heart Sound Classification. J. Medical Imaging Health Informatics 11(2): 513-528 (2021). https://doi.org/10.1166/jmihi.2021.3287

[14] Kholoud Maswadi, Norjihan Abdul Ghani, Suraya Hamid, Muhammad Babar Rasheed: Human activity classification using DT and Naive Bayes classifiers. Multim. Tools Appl. 80(14): 21709-21726 (2020). https://doi.org/10.1007/s11042-020-10447-x

[15] Yousef Ali Khan, Q. S. Shan, Qianning Liu, Syed Zaheer Abbas: A nonparametric copula-based DT for two random variables using MIC as a classification index. Soft Comput.25 (15): 9677-9692 (2020). https://doi.org/10.1007/s00500-020-05399-1

[16] Yashesh D. Dhebar, Kalyanmoy Deb: Interpretable Rule Discovery through Bilevel Optimization of Split-Rules of Nonlinear DTs for Classification Problems. IEEE Trans. Cybern. 51(11): 5573-5584 (2020). https://doi.org/10.1109/TCYB.2020.3033003

[17] Jugal Patel, Jeffrey Katan, Liliana Perez, Raja Sengupta: Transferring decision boundaries onto a geographic space: Agent rules extracted from movement data using classification trees. Trans. GIS 25(3): 1176-1192 (2021). https://doi.org/10.1111/tgis.12770

[18] B. Durgalakshmi, V. Vijayakumar: Feature selection and classification using support vector machine and DT.Comput. Intell. 36(4): 1480-1492 (2020). https://doi.org/10.1111/coin.12280

[19] Mahdi Abbasi, Aazad Shokrollahi: Enhancing the performance of DT-based packet classification algorithms using CPU cluster. Clust. Comput. 23(4): 3203-3219 (2020). https://doi.org/10.1007/s10586-020-03081-7

[20] Stathis Malakis, Panagiotis Psaros, Tom Kontogiannis, Christina Malaki: Classification of air traffic control scenarios using DTs: insights from a field study in terminal approach radar environment. Cogn. Technol. Work. 22(1): 159-179 (2019). https://doi.org/10.1007/s10111-019-00562-7