INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue I, January 2025
www.ijltemas.in
Page 201
Academic Study Plan Recommender and Simulator System Using
Forward Chaining and Heuristic Algorithms
Criselle J. Centeno
1
, Jonilo Mababa
2
, Isagani Mirador Tano
3
, Keno Piad
4
, Ace Lagman
5
, Joseph
Espino
6
, Jayson Victoriano
7
1,2
Graduate School Department, La Consolacion University, Bulihan, City of Malolos, Bulacan, Philippines
4,7
Graduate School Department, Bulacan State University, Malolos, Bulacan, Philippines
3
Graduate School Department, Quezon City University, Sanbartolome, Quezon City, Philippines
5
Graduate School Department, Far Eastern University, Sampaloc, Manila, Philippines
6
Graduate School Department, Bulacan State University, Bulihan, City of Malolos, Bulacan, Philippines
DOI : https://doi.org/10.51583/IJLTEMAS.2025.1401021
Received: 24 January 2025; Accepted: 01 February 2025; Published: 17 February 2025
Abstract— The Academic Study Plan Recommender and Simulator System introduces an innovative approach to academic
planning, combining Forward Chaining and Heuristic Algorithms to generate personalized and optimized study plans. Forward
Chaining enables the dynamic evolution of plans by iteratively applying rules based on individual academic goals, elective
preferences, and constraints. Heuristic Algorithms enhance this process by prioritizing courses based on factors such as relevance,
difficulty, and scheduling, ensuring optimal decision-making and improved user satisfaction. The system’s simulator component
further empowers students by enabling them to explore various academic scenarios and adapt to changes like elective choices or
shifts in majors. Feedback from IT experts revealed a 90% call for algorithmic improvements, emphasizing the need for enhanced
reliability and performance, even though satisfaction with the system reached 76.8%. Functional suitability received an overall
satisfaction rating of 4.27, with high ratings for functional correctness and appropriateness from both faculty and irregular
students. Performance efficiency and usability achieved similarly strong ratings, averaging 4.26 and 4.21, respectively. Key
usability factors like appropriateness recognizability, operability, and user interface design contributed significantly to user
satisfaction. Additionally, reliability and security scored highly, averaging 4.40 and 4.26, underscoring the system's dependable
and secure operations. Flexibility and compatibility were also commended, with average ratings of 4.27, reflecting the system’s
adaptability and seamless integration with other tools and processes. Maintainability received a high score of 4.23, demonstrating
the system’s ease of modification and testing. Faculty and irregular students particularly appreciated features such as modularity,
operability, and learnability, which align with studies highlighting the importance of these factors in educational technologies. By
digitizing the academic planning process, the system reduces manual effort for instructors and students while delivering accurate,
adaptive study plans tailored to individual needs. The results affirm the system’s capability to enhance user experiences and
support educational success through personalized and optimized planning.
Keywords— Academic Study Planning, Forward Chaining, Heuristic Algorithms, Usability and Satisfaction Educational
Technology Optimization
I. Introduction
In the evolving educational landscape, students face challenges in creating effective study plans due to factors like learning styles,
academic performance, time constraints, and resource availability. Algorithmic systems, particularly those using forward chaining
and heuristic algorithms, offer a structured yet flexible approach to study planning. Forward chaining logically sequences courses
based on prerequisites, while heuristics optimize time management, task prioritization, adaptability, and study plan efficiency.
The system dynamically allocates study time by analyzing available hours and recommending structured sessions using
techniques like spaced repetition and Pomodoro strategies to maximize retention. It prioritizes subjects based on student
performance, ensuring areas needing improvement receive more focus. Additionally, it adapts to individual learning preferences
by recommending study subjects to focus on, to tailor to the student's engagement style. Through heuristic optimization methods
like greedy algorithms, simulated annealing, and genetic algorithms, the system generates the most efficient study sequences,
balancing workload and prerequisite requirements to prevent academic overload. This research aims to bridge theoretical
principles with practical applications by developing a personalized, adaptive, and optimized study plan recommender and
simulator system, ultimately improving academic efficiency and student outcomes.
Significance of the Study
The following shall benefit from this study:
1. Students. The study aims to create a system that specializes study plans based on individual students' academic history,
constraints, and academic needs. This customization can lead to more effective learning experiences, addressing the
diverse needs of students with varying learning styles and capabilities. On the other hand, students may experience
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue I, January 2025
www.ijltemas.in
Page 202
reduced stress and anxiety related to academic performance. Knowing that they have a structured approach to their
studies can contribute to a more positive and focused learning environment.
2. Academic Advisors. Advisors play a crucial role in guiding irregular students through their academic challenges. They
use the study plan recommender system to gain insights into students' academic progress, strengths, and areas that need
improvement.
3. Institutional Administrators. Decision-makers within educational institutions endorse and integrate the study plan
recommender system into the academic support infrastructure. They oversee the system's implementation, ensuring that
it aligns with the institution's goals for supporting irregular students. Administrators may also allocate resources and
provide institutional support for the system's ongoing development and improvement. Researchers/Developers. This
study may serve as a valuable case study for future researchers and developers by providing insights into algorithmic
development, user-centric design, adaptive learning environments, interdisciplinary collaboration, ethical considerations,
and continuous improvement in the realm of educational technology. This foundation can inspire further innovation and
advancements in the field.
Scope and Delimitation
The scope of this study includes the development and implementation of an Academic Study Plan Recommender and Simulator
System that utilizes Forward Chaining and Heuristic Algorithms. The system is designed to help students and academic advisors
by allowing them to review past study plans and generate customized study schedules based on individual academic histories.
One of its key features is its ability to specifically assist students who have failed one or more subjects, helping them restructure
their study plans to improve performance. By analyzing a student’s academic records, the system generates a study schedule that
optimizes course sequencing, ensuring that students can catch up efficiently while meeting institutional requirements.
The delimitation of this study defines its boundaries, limiting the system’s functionality to generating study plans within the
Academic Study Plan Recommender and Simulator System. The study does not extend to creating educational materials such as
textbooks, video lectures, or interactive learning modules. Instead, it focuses on recommending and simulating study schedules
based on available course offerings, academic performance, and prerequisite requirements. Additionally, the system does not
involve academic counseling, direct intervention in curriculum decisions, or automated grading. These exclusions ensure that the
research remains targeted and efficient, concentrating solely on providing structured academic planning rather than expanding
into unrelated areas. By maintaining this well-defined scope, the study ensures that the system remains focused on its core
purpose—enhancing students' ability to plan and improve their academic journeys through personalized, data-driven
recommendations.
II. Methodology
This study employed a quantitative research approach with elements of mixed-methods research, integrating structured surveys
and statistical analysis to assess the development of an academic study planning tool. A comprehensive literature review was
conducted to explore existing methodologies in study planning and recommender systems. The system, incorporating forward
chaining and heuristic algorithms, was designed and developed to generate personalized study plans. Purposive sampling was
used to select faculty members and irregular students as participants, ensuring diverse insights into study plan creation. Faculty
members contributed expertise in academic structuring, while irregular students provided user-centered feedback for system
improvement.
System effectiveness was evaluated using ISO 25010 standards, measuring performance through precision metrics, and validated
through user feedback surveys. A questionnaire, incorporating Likert scale items and open-ended questions, captured data on
participants’ academic preferences and study habits. Statistical analysis was conducted to identify correlations between study plan
recommendations and academic performance. Through these integrated methods, the study aimed to develop a personalized, data-
driven academic planning tool to enhance students' learning experiences.
Respondents of the Study
The respondents of the study may include undergraduate and graduate students from various academic disciplines enrolled in
State Universities or Colleges offering diverse courses. These students may be irregular in their academic progress or seeking
personalized study plans to accommodate their unique needs and preferences. Additionally, educators, academic advisors, and
administrators involved in academic planning and curriculum development may also serve as respondents to provide insights into
the effectiveness and usability of the study plan recommender and simulator system.
Frequency and Percentage Distribution of Respondents
The qualitative phase of the study gathers insights from students, educators, academic advisors, and administrators to understand
academic planning challenges, particularly for irregular students and those needing personalized study plans. Through interviews
and open-ended survey responses, key themes such as flexible scheduling, subject prioritization, and study material preferences
are identified, ensuring the system aligns with user needs. To analyze respondent demographics, the study employs frequency and
percentage distribution, categorizing participants by educational level, enrollment status, field of study, and academic role. This
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue I, January 2025
www.ijltemas.in
Page 203
statistical method determines representation balance, with frequency showing respondent counts per category and percentage
distribution measuring proportions relative to the total sample. For example, if 60% of respondents are irregular students, their
high representation validates the study's focus on personalized academic planning. These findings help refine the *study plan
recommender and simulator system*, ensuring it effectively addresses user needs.
Sampling Techniques
The study used a quantitative research approach to develop and implement an academic study planning tool, integrating
forwarding chaining and heuristic algorithms. A comprehensive literature review was conducted to explore existing
methodologies in study planning and recommender systems. Participants were selected using purposive sampling to provide
diverse academic backgrounds. The system's effectiveness was evaluated using ISO 25010, focusing on precision, and user
feedback was gathered through online surveys. A questionnaire was developed to capture participants' academic preferences and
study habits, and statistical analysis identified patterns between academic performance and study plan recommendations, aiming
to improve personalized learning experiences.
Frequency and Percentage Distribution of Respondents
The qualitative phase of the study gathers insights from students, educators, academic advisors, and administrators to understand
academic planning challenges, particularly for irregular students and those needing personalized study plans. Through interviews
and open-ended survey responses, key themes such as flexible scheduling, subject prioritization, and study material preferences
are identified, ensuring the system aligns with user needs. To analyze respondent demographics, the study employs frequency and
percentage distribution, categorizing participants by educational level, enrollment status, field of study, and academic role. This
statistical method determines representation balance, with frequency showing respondent counts per category and percentage
distribution measuring proportions relative to the total sample. For example, if 60% of respondents are irregular students, their
high representation validates the study's focus on personalized academic planning. These findings help refine the *study plan
recommender and simulator system*, ensuring it effectively addresses user needs.
Locale of the Study
The locale of the study encompasses a diverse range of State and College Universities (SUCs), including Adamson University,
Bulacan State University, Centro Escolar University, ICCT Colleges, Lyceum of the Philippines University, Our Lady of Lourdes
Technological College, Pamantasan ng Lungsod ng Valenzuela, PMI Colleges, Inc., Rizal Technological University, Santa Isabel
College of Manila, Technological University of the Philippines, Universidad De Manila, University of Makati, University of the
Philippines – Diliman, and the University of Santo Tomas. This study was conducted in collaboration with these institutions to
develop the Academic Study Plan Recommender and Simulator System using Forward Chaining and Heuristic Algorithms.
Instruments of the Study/Data Collection
The primary tool for data collection will be a survey questionnaire designed to quantitatively assess the competencies and
practices of individuals within State Universities and Colleges. Utilizing a 5-point Likert scale, the questionnaire will gauge the
perspectives and practices of these individuals across various criteria and domains using ISO 25010, the questionnaire consists of
three parts:
Part I: Demographic information of participants, including their institution of enrollment, course, current year of study, and the
year they became an irregular student, along with the reason for this status.
Part II: Assessment of participants' practices in using and creating manual study plans every semester.
Part III: Evaluation of users' perspectives on competencies across domains using the ISO 25010. These instruments serve as the
foundation for data collection, analysis, and validation, thereby ensuring the accuracy and reliability of study outcomes. By using
appropriate instruments specialized to the study's objectives, the researcher can gain valuable insights into the efficacy and
usability of the study plan recommender and simulator system, ultimately contributing to advancements in educational
technology.
Data Collection
This study utilizes a survey-questionnaire method as the primary data collection approach to obtain insights from participants
regarding their academic planning experiences and preferences. The survey-questionnaire method allows for a structured and
standardized way of collecting data, ensuring consistency and comparability across responses. This approach enables researchers
to gather quantifiable data while also capturing participants’ subjective experiences related to study planning.
To interpret the collected responses, the study employs a 5-Point Likert Scale Method, which provides a standardized framework
for measuring participants' attitudes, perceptions, and preferences. Each response is assigned a numerical value, typically ranging
from 1 (Strongly Disagree) to 5 (Strongly Agree), ensuring a clear and consistent method of quantification. This allows for a
more precise analysis of trends and patterns in participants’ feedback. The Likert Scale also helps in identifying the degree of
agreement or disagreement with specific statements related to the system’s usability, effectiveness, and impact on academic
planning.
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue I, January 2025
www.ijltemas.in
Page 204
The survey is designed to include *both closed-ended and open-ended questions. Closed-ended questions, utilizing the Likert
Scale, facilitate statistical analysis by providing numerical data that can be examined for patterns and correlations. Meanwhile,
open-ended questions allow participants to provide qualitative feedback, offering deeper insights into their experiences and
suggestions for system improvement.
By employing this structured data collection method, the study ensures that the gathered information is reliable, quantifiable, and
reflective of participant experiences, ultimately aiding in the evaluation and refinement of the Academic Study Plan
Recommender and Simulator System.
Table 1. 5-point Likert Scale
Response Categories
Numerical Value
Strongly Agree
5
Agree
4
Neither Agree nor Degree
3
Disagree
2
Strongly Disagree
1
Additionally, to understand respondents’ perspectives on competencies across domains using ISO 25010. The study utilized
another 5-point Likert Scale to serve as a straightforward method for clarifying data and simplifying the evaluation of
competencies, aiding in the study's analysis and interpretation, with the numerical ranges interpreted as follows:
Table 2. 5-point Likert Scale for Effectiveness of the System
Response Categories
Numerical Value
Ver Satisfied
4.21 - 5.00
Satisfied
3.41 - 4.20
Neutral
2.61 - 3.40
Dissatisfied
1.81 - 2.60
Very Dissatisfied
1.00 - 1.80
By categorizing responses in this manner, the study can easily assess the level of satisfaction and effectiveness regarding the
utilization of the study plan recommender and simulator system, providing insights into competencies and areas for potential
enhancement.
III. Results and Discussions
This chapter provides interpretation of the data collected throughout the study. Its primary goal is to offer insights into how the
study and system tackles the complexities and challenges identified in preceding chapters. The presentation of findings is
structured to offer a cohesive narrative of the study's operational dynamics within real-world educational contexts. It critically
evaluates the system's strengths, weaknesses, and potential avenues for improvement, informed by empirical data and user
feedback.
Results
Quantitative Phase
For clarity and consistency, the data are presented in the sequence of the research questions outlined in Chapter 1: (1)
respondents' profiles (age, gender, academic rank, position, years of teaching, and educational qualifications); (2) their
perspectives on the system's competencies based on ISO 25010 quality domains (functional suitability, performance efficiency,
compatibility, usability, reliability, security, maintainability, and portability); (3) practices of the system's competencies in
communication, decision-making, adaptability, task management, and empowerment; and (4) analysis using the Weighted Mean
to interpret results and implications.
1. Profile of Respondents: This section provides a comprehensive overview of the respondents’ backgrounds to understand the
diversity and distribution of the sample population involved in the study.
School/University: Table 3 presents the distribution of respondents by school/university. The largest group (7.40%) was from
Adamson University, followed by Arellano University (7.33%) and Bulacan State University (7.25%). Other institutions, such as
Centro Escolar University, ICCT Colleges, and several others, each accounted for around 7%. The smallest group was from the
University of the Philippines – Diliman, with 2.49%.
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue I, January 2025
www.ijltemas.in
Page 205
Table 3. Frequency and Percentage Distribution of Respondents in Terms of School/University
School/University
Frequiency
Percent
Rank
Adamson University
101
7.40%
1
Arellano University
82
7.33%
2
Bulacan State University
100
7.25%
3
Centro Escolar University
101
7.18%
4
ICCT Colleges
103
7.18%
4
Lyceum of the Philippines University
99
7.11%
5
Our Lady of Lourdes Technological
College
100
7.11%
5
Pamantasan ng Lungsod ng Maynila
80
7.11%
5
Pamantasan ng Lungsod ng
Valenzuela
102
7.11%
5
PMI Colleges, Inc.
99
7.11%
5
Rizal Technological University
100
7.04%
6
Santa Isabel College of Manila
100
7.04%
6
Technological University of the
Philippines
100
5.83%
7
Universidad De Manila, University of
Manila
104
5.69%
8
University of the Philippines -
Diliman
35
2.49%
9
Total
1406
100.0
2. Perspectives on the Recommender System: The competencies of the Academic Study Plan Recommender and Simulator
System are evaluated based on the ISO 25010 quality model, which provides a standardized framework for system assessment.
This approach ensures consistency, facilitates comparability across projects, and establishes clear quality benchmarks, promoting
better communication among stakeholders regarding expectations and outcomes (Abran et al., 2021). The system’s competencies
are categorized into eight domains: functional suitability, performance efficiency, compatibility, usability, reliability, security,
maintainability, and portability.
Table 4 shows high satisfaction with the system’s functional suitability. Functional correctness was rated "satisfied" by professors
(WM = 3.92) and "very satisfied" by students (WM = 4.33), with an overall rating of "satisfied" (WM = 4.13). Functional
appropriateness received similar ratings, with an overall "satisfied" rating (WM = 4.18). These results demonstrate the system's
effectiveness in academic planning.
Table 4. Weighted Mean Rating on the Perspectives of the Respondents in Functional Suitability
Functional Suitability
Faculty
Members
WM NV
Irregular
Students WM
NV
Overall
NV
1. Functional
Correctness
3.92 S
4.33 S
4.13
S
2. Functional
Appropriateness
4.14 S
4.21 S
4.18
S
Average Mean
4.03
4.27
4.155
VS
Table 5 shows high satisfaction with the system's maintainability. Modularity and modifiability were rated "very satisfied" overall
(WM = 4.34 and WM = 4.26, respectively), while analyzability was also rated "very satisfied" (WM = 4.22). Reusability and
testability received "satisfied" ratings (WM = 4.08 and WM = 4.17). These results highlight the system’s robustness and
adaptability for academic planning.
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue I, January 2025
www.ijltemas.in
Page 206
Table 5. Weighted Mean Rating on the Perspectives of the Respondents in Maintainability
Functional
Suitability
Faculty
MembersW
M NV
Irregular
Students
WM NV
Overall
NV
1. Modularity
4.28
VS
4.4 S
4.34
VS
2. Reusability
4.07 S
4.08 S
4.08
S
3. Analyzability
4.14 S
4.29
VS
4.22
VS
4. Modifiability
4.29
VS
4.21
VS
4.26
VS
5. Testability
4.14 S
4.19 S
4.17
S
Average Mean
4.18
4.23
4.23
VS
Overall, the respondents perceived a very high level of satisfaction with the maintainability of the system, with an average
weighted mean of 4.23, categorized as very satisfied. This suggests that the system is considered easy to maintain, modify, and
test, contributing to its overall reliability and efficiency in use.
Qualitative Phase
The quantitative phase of the study involved rigorous data collection and analysis to complement the qualitative insights gained
earlier. Following the principles outlined by Australian Aid (2019) for mixed-methods research, this phase aimed to quantify and
validate the findings from the qualitative phase through structured surveys and statistical analysis. ISO 25010 was utilized for
robust data analysis and interpretation. The quantitative findings provided valuable insights into the effectiveness and user
perceptions of the Academic Study Plan Recommender and Simulator System.
Table 6. Insights of the Respondents using Qualitative Phase for Impact and Outcome Needs
Questions
Respondents Response
Respondents who
Agreed
1. How effectively do the recommended
study plans align with your specific
academic goals and career aspirations?
“The study plans align well with my academic goals
and career aspirations.”
“The study plans show moderate alignment with my
goals, requiring additional customization.”
1051
355
2. What is the perceived impact of using the
Academic Study Plan Recommender and
Simulator System on your academic
success, efficiency in course planning, and
overall satisfaction with your academic
journey?
“I have experienced significant improvements in
academic success, course planning efficiency, and
overall satisfaction.”
“I have seen moderate improvements in academic
success and course planning efficiency, with some
increase in overall satisfaction.”
1153
253
Table 6 presents insightful qualitative data on respondents' perspectives regarding the impact and alignment of the system with
their academic goals and satisfaction levels. In response to the alignment with academic goals and career aspirations, the findings
indicate that a significant number of respondents (1051) felt the recommended study plans aligned well with their specific
academic and career objectives. This suggests that the system effectively tailored study plans to meet their needs. However, 355
respondents mentioned that while the study plans showed moderate alignment, they believed additional customization was
necessary for better alignment with their goals, highlighting the diversity in user expectations and needs.
Table 7. Insights of the Respondents using Qualitative Phase for Customization and Personalization Needs
Questions
Respondents Response
Respondents who
Agreed
1. How effectively do the recommended
study plans align with your specific
academic goals and career aspirations?
“The study plans align well with my academic goals
and career aspirations.”
“The study plans show moderate alignment with my
goals, requiring additional customization.”
1051
355
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue I, January 2025
www.ijltemas.in
Page 207
2. What is the perceived impact of using
the Academic Study Plan Recommender
and Simulator System on your academic
success, efficiency in course planning, and
overall satisfaction with your academic
journey?
“I have experienced significant improvements in
academic success, course planning efficiency, and
overall satisfaction.”
“I have seen moderate improvements in academic
success and course planning efficiency, with some
increase in overall satisfaction.”
1153
253
Table 7 presents qualitative insights into how users perceive the customization and personalization features. Regarding the
customization of study plans, most respondents (1066) indicated that the system allows a high degree of customization to fit their
individual academic needs and constraints. This positive feedback suggests that these users find the system flexible and
responsive, enabling them to personalize their study plans effectively. However, 340 respondents expressed that the system offers
only limited customization options, which they found challenging to adapt to their specific academic requirements.
IV. Conclusions and Recommendations
Summary of Findings
The key findings of this study have been summarized and are presented in accordance with the research questions and statement
of the problems in Chapter 1. The significant findings of this study are as follows:
Conclusions
Upon evaluation of the study, the researcher derived the following conclusive findings:
1. Algorithms personalize study plans by analyzing data points such as prerequisites, performance, learning styles, and
curriculum requirements. Using forward chaining and heuristic techniques, they develop accurate schedules, evidenced
by high ratings in Functional Stability, Performance Efficiency, and Usability. Continuous evaluation ensures plans
adapt to students’ evolving needs.
2. Heuristic optimization enhances decision-making by integrating learning styles, pace, and feedback, ensuring study
plans meet individual needs. High ratings in Functional Stability and Performance Efficiency reflect its effectiveness.
Adaptive heuristics provide practical, flexible solutions that evolve with new data.
3. Study plan constraints include academic history, performance, curriculum requirements, time availability, credit loads,
and deadlines. These ensure tailored and feasible plans aligned with institutional standards and academic goals.
4. Forward chaining uses initial data to infer additional insights, generating dynamic, personalized study plans that evolve
with student progress. It ensures logical course sequencing and an achievable academic path.
5. Feedback mechanisms under ISO 25010 standards continuously improve system performance and usability through
surveys, user input, and monitoring. Regular updates ensure study plans remain user-centric and effective.
Recommendations
Based on the findings and conclusions of the study, the following recommendations are provided to enhance the system's
effectiveness and usability:
1. Educational institutions should integrate advanced algorithms into academic advisory systems to create personalized
study plans using data like prerequisites, performance, learning preferences, and curriculum requirements. Regular
monitoring ensures these plans adapt to evolving student needs and institutional goals.
2. Institutions should implement feedback loops where students contribute to refining study plans, enabling heuristic
algorithms to adapt effectively. Collaboration with academic advisors ensures recommendations align with institutional
standards, fostering student success and satisfaction.
3. Establishing clear constraints for study plan generation ensures alignment with academic policies and curriculum
requirements. Institutions should regularly update constraints, communicate them transparently, and provide guidelines
to help students make informed decisions.
4. Forward Chaining algorithms enhance study plan recommendations by dynamically building on initial data to provide
precise and adaptive plans. Institutions should implement these algorithms, train advisors, and regularly refine inference
rules for optimal effectiveness.
5. Adopting the ISO 25010 framework helps institutions evaluate and improve study plan systems. Structured feedback
mechanisms, like surveys and focus groups, enable continuous improvement, boosting functionality, user satisfaction,
and system effectiveness.
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue I, January 2025
www.ijltemas.in
Page 208
References
1. Ajibade, S. S. M., Ahmad, N. B., & Shamsuddin, S. M. (2019, August). A heuristic feature selection algorithm to
evaluate academic performance of students. In 2019 IEEE 10th Control and System Graduate Research Colloquium
(ICSGRC) (pp. 110-114). IEEE.
2. Alghamdi, H., Alsubait, T., Alhakami, H., & Baz, A. (2020). A review of Optimization Algorithms for university
timetable scheduling. Engineering, Technology & Applied Science Research, 10(6), 6410–6417.
https://doi.org/10.48084/etasr.3832
3. Almonteros, J. R., Pacot, M. P. B., & Pitogo, V. A. (2022, December). Automation of Curriculum-based Student-Subject
Encoding: A Web Application. In Proceedings of the 2022 11th International Conference on Networks, Communication
and Computing (pp. 328-333).
4. Almonteros, J. R., Phil, M., & Pitogo, V. A. (2022). Automation of Curriculum-based Student-Subject Encoding: A Web
Application. https://doi.org/10.1145/3579895.3579944
5. Aslan, A., Bakir, I., & Vis, I. F. A. (2020). A dynamic thompson sampling hyper-heuristic framework for learning
activity planning in personalized learning. European Journal of Operational Research.
https://doi.org/10.1016/j.ejor.2020.03.038
6. Asthana, P., & Hazela, B. (2019). Applications of machine learning in improving learning environment. In Intelligent
systems reference library (pp. 417–433). https://doi.org/10.1007/978-981-13-8759-3_16
7. Kaveh, A., Hamedani, K. B., Hosseini, S. M., & Bakhshpoori, T. (2020). Optimal design of planar steel frame structures
utilizing meta-heuristic optimization algorithms. Structures, 25, 335–346. https://doi.org/10.1016/j.istruc.2020.03.032
8. Kenekayoro, P., & Fawei, B. (2020). Meta-Heuristic Solutions to a Student Grouping Optimization Problem faced in
Higher Education Institutions. ArXiv.org. https://arxiv.org/abs/2010.00499
9. Kola, M. (2019). Pre-service teachers’ action research: technology education lesson planning in a South African
University. Educational Action Research, 1–19. https://doi.org/10.1080/09650792.2019.1686043
10. Labuanan, F. R. E., Tapaoan, S. J. E., & Camungao, R. Q. (2019). Application of representation and fitness method of
genetic algorithm for class scheduling system. Int. J. Recent Technol. Eng, 8(2), 1816-1821.
11. Li, S., & Liu, T. (2021). Performance Prediction for Higher education students using Deep learning. Complexity, 2021,
1–10. https://doi.org/10.1155/2021/9958203
12. Rashad, A. (n.d.). Forward and Backward Chaining Techniques of Reasoning in Rule-Based Systems. http://i-
rep.emu.edu.tr:8080/jspui/handle/11129/2325
13. Romero II, V. M., Santiago, B. D., & Nuevo, J. M. Z. (2023). A hybrid recommendation scheme for delay-tolerant
networks: The case of digital marketplaces. Array, 19, 100299.
14. Rosas, P., Ríos-Solís, Y. Á., & Romeo Sánchez Nigenda. (2023). Scheduling personalized study plans considering the
stress factor. Interactive Learning Environments, 1–20. https://doi.org/10.1080/10494820.2023.2191260
15. Zheng. W. (2022) Cluster Analysis Algorithm in the Analysis of College Students’ Mental Health Education.
https://www.hindawi.com/journals/abb/2022/6394707/
16. Zhou, S., Dai, X., Chen, H., Zhang, W., Ren, K., Tang, R., He, X., Yu, Y. (2020) Interactive Recommender System via
Knowledge Graph-enhanced Reinforcement Learning. https://dl.acm.org/doi/abs/10.1145/3397271.3401174
