Artifact: Predictive Model Initiative Project (EME 6348, Predictive Learning Analytics)
Role: Sole Analyst and Designer
Type of Project: Predictive analytics model and intervention planning report

Rationale for Selecting This Artifact

This artifact was selected because it demonstrates the use of assessment data and learning analytics to inform decisions about instructional supports and learning environments. The project required analyzing longitudinal student assessment data to identify learners at risk of not meeting reading benchmarks and translating predictive insights into actionable instructional interventions. The artifact provides evidence of data-informed decision-making intended to improve learning conditions, resource allocation, and targeted instructional support.

AECT Standard 3.3 – Learning Environments

Candidates demonstrate the ability to use assessment data and research evidence to inform the design and improvement of learning environments.

This artifact demonstrates AECT Standard 3.3 through the application of predictive analytics to longitudinal assessment data in order to identify students at risk of academic failure. Assessment data from multiple progress monitoring periods were cleaned, analyzed, and modeled to forecast performance on future standardized reading assessments. These predictions were explicitly connected to decisions about instructional interventions and learning supports, including individualized learning plans, targeted tutoring, and professional development for educators.

The project demonstrates how assessment data can be used not only to describe past performance but to proactively shape learning environments. By identifying risk patterns early, the model supports timely instructional adjustments and strategic resource allocation, illustrating evidence-based decision-making aimed at improving student outcomes. The artifact reflects applied learning analytics practice grounded in instructional improvement rather than retrospective reporting.

Competencies Demonstrated

• Competency: Analyze learner performance data

This artifact demonstrates Analyze learner performance data through the cleaning, normalization, and longitudinal analysis of student assessment scores across grade levels. The project required examining trends, identifying risk thresholds, and interpreting performance trajectories to inform predictive modeling.

• Competency: Use data to inform instructional decisions

This artifact demonstrates Use data to inform instructional decisions by translating model outputs into concrete intervention strategies. Predictive findings were used to recommend instructional supports such as targeted tutoring, individualized learning plans, and professional development, demonstrating the ability to connect analytics to instructional action.

• Competency: Evaluate learning outcomes

This artifact demonstrates Evaluate learning outcomes through validation of predictive models using statistical measures such as R² and cross-validation. Model performance was assessed to ensure reliability before instructional recommendations were made, reflecting responsible data-informed evaluation.

Artifact: Research Group Summary & Reflection (EME 7615, Game-Based Learning Research)
Role: Research Group Member and Reflective Analyst
Type of Project: Weekly research summaries and culminating reflective analysis

Rationale for Selecting This Artifact

This artifact was selected because it documents the collaborative creation, evaluation, and refinement of game-based learning environments within a research context. The weekly summaries and final reflection capture how instructional design decisions evolved through group discussion, iterative feedback, and examination of emerging technologies such as Text-to-Game systems and the Saboteur prototype. The artifact provides evidence of reflective practice, collaborative design thinking, and data-informed evaluation applied to the development of learning environments over time.

AECT Standard 3.1 – Creating Learning Environments

Candidates demonstrate the ability to create instructional and learning environments that facilitate learning and improve performance.

This artifact demonstrates AECT Standard 3.1 through analysis of how game-based learning environments are conceptualized, designed, and iteratively refined within a collaborative research group. The reflection documents how instructional intent, learner engagement, narrative structure, and interactivity are considered together when designing environments such as Text-to-Game systems and the Saboteur platform. These environments are examined not as static products, but as evolving systems shaped by instructional goals, user interaction, and design constraints.

The artifact also highlights collaborative creation as a key component of learning environment design. Group discussion, shared critique, and division of design labor are described as mechanisms for generating and refining ideas. This demonstrates understanding that effective learning environments often emerge from team-based design processes rather than individual authorship alone, aligning with professional practice in instructional design and educational technology.

AECT Standard 3.3 – Using Evidence to Improve Learning Environments

Candidates demonstrate the ability to use data, research, and evaluation evidence to improve learning environments.

This artifact demonstrates AECT Standard 3.3 through reflection on how user feedback, analytics, and research insights inform the refinement of game-based learning environments. The document discusses the role of user engagement data, behavioral patterns, and iterative feedback in shaping design decisions for Text-to-Game and Saboteur technologies. These reflections emphasize how evidence is used to guide revisions to mechanics, narrative complexity, and user experience in order to improve instructional effectiveness.

The artifact further demonstrates evaluative thinking by acknowledging challenges such as scalability, platform compatibility, and uneven group contribution, and by connecting these challenges to broader design considerations. This reflective evaluation illustrates how learning environments are improved over time through evidence-based iteration rather than one-time design decisions.

Competencies Demonstrated

• Competency: Collaborate in instructional design and development

This artifact demonstrates Collaborate in instructional design and development through sustained participation in a research group focused on game-based learning. The reflection documents how ideas were shared, refined, and negotiated within the group, illustrating the ability to work productively in a collaborative design context and to contribute to collective problem-solving.

• Competency: Evaluate learning environments

This artifact demonstrates Evaluate learning environments by critically examining the strengths and limitations of emerging game-based platforms. Evaluation is grounded in learner engagement, usability, scalability, and instructional coherence rather than personal preference, reflecting professional evaluative judgment.

• Competency: Use data and feedback to inform design decisions

This artifact demonstrates Use data and feedback to inform design decisions through discussion of how user analytics, engagement patterns, and iterative feedback inform ongoing refinement of learning environments. The reflection emphasizes that data-informed iteration is essential for improving both instructional effectiveness and user experience in game-based learning systems.

• Competency: Engage in reflective practice

This artifact demonstrates Engage in reflective practice through critical self-assessment of group processes, design challenges, and instructional outcomes. The reflection connects course concepts to real-world development trajectories, illustrating the ability to evaluate one’s own learning and professional growth within instructional design contexts.

Artifact: Educational Game Concept – AI-Driven Learning Game (M5 – EME 6936)
Role: Sole Designer and Concept Author
Type of Project: Conceptual design document for an adaptive, AI-supported educational game

Rationale for Selecting This Artifact

This artifact was selected because it demonstrates the ability to design learner-centered support structures within an educational game environment through informed selection of instructional resources and adaptive technologies. The project required conceptualizing how artificial intelligence could be used to personalize instruction, scaffold learning, and provide responsive feedback to elementary learners. The artifact provides evidence of intentional learning-environment design that prioritizes learner support, adaptability, and instructional responsiveness rather than static content delivery.

AECT Standard 3.2 – Learner Support (Primary Alignment)

Candidates demonstrate the ability to design and implement learner support strategies within learning environments.

This artifact demonstrates AECT Standard 3.2 through the design of adaptive learner support mechanisms embedded within the proposed game environment. The concept outlines how an AI-driven system would monitor learner performance indicators—such as accuracy, response time, and error patterns—and dynamically adjust instructional difficulty, pacing, and feedback. These mechanisms are designed to ensure that learners receive appropriate support based on their individual needs, preventing both cognitive overload and disengagement.

Learner support is further demonstrated through the inclusion of scaffolded hints, mini-tutorials, visual aids, and branching gameplay paths that respond to learner performance. Narrative elements, such as the guiding character within the game, are also leveraged as support structures to provide encouragement, clarification, and progress summaries. Together, these design features reflect an understanding of how learner support can be integrated directly into interactive learning environments to promote persistence, comprehension, and skill development.

AECT Standard 3.4 – Managing (Secondary Support)

Candidates demonstrate the ability to manage the use of processes and resources to support learning and performance.

This artifact provides secondary support for AECT Standard 3.4 at a conceptual level by outlining how instructional processes and technological resources would be coordinated within an AI-driven learning system. The design specifies how performance data would be collected, interpreted, and reused over time to update learner profiles and inform subsequent instructional decisions. While the project does not involve implementation or system administration, it demonstrates awareness of how data flows, adaptive algorithms, and instructional content must be organized and managed to function cohesively within a learning environment.

This conceptual management perspective reflects early-stage instructional systems thinking, showing how instructional resources, learner data, and adaptive logic interact to sustain an effective learning experience. The alignment to 3.4 is therefore limited but defensible as conceptual planning rather than operational management.

AECT Standard 3.5 – Ethics (Secondary, Light Support)

Candidates demonstrate the ability to design learning environments that are ethical, equitable, and responsible.

This artifact offers limited secondary support for AECT Standard 3.5 through its emphasis on equitable learner treatment within adaptive systems. The concept explicitly aims to prevent learners from being overwhelmed or under-challenged by adjusting difficulty and support based on performance data. This reflects ethical instructional intent by prioritizing learner well-being, fairness, and developmental appropriateness.

While the project does not explicitly address issues such as data privacy, algorithmic bias, or accessibility compliance, its learner-centered design philosophy demonstrates emerging ethical awareness in the use of AI-supported instructional technologies. As such, alignment to 3.5 should be treated as supportive rather than primary.

Competencies Demonstrated

• Competency: Select instructional resources

This artifact demonstrates Select instructional resources through the intentional selection of adaptive AI mechanisms, narrative supports, visual aids, and feedback strategies to support math learning. Resource selection is grounded in instructional purpose and learner needs rather than technological novelty.

• Competency: Design learner support strategies

This artifact demonstrates Design learner support strategies by embedding scaffolding, feedback, and adaptive pathways directly into the game environment. Support mechanisms are aligned to learner performance and instructional goals, reflecting informed design of responsive learning environments.

• Competency: Analyze learner performance data (Conceptual)

This artifact demonstrates Analyze learner performance data at a conceptual level by specifying how performance metrics would be collected and interpreted to guide instructional adaptation. While no live data analysis is conducted, the design reflects understanding of how learner data informs instructional decisions within adaptive systems.

• Competency: Engage in instructional systems thinking

This artifact demonstrates Engage in instructional systems thinking through its holistic view of how learners, content, feedback, and adaptive technologies interact within a learning environment. The concept reflects awareness of interdependencies among instructional components rather than isolated design elements.