student_profile:
demographics:
- field: age
type: integer
min: 0
max: 120
example: 16
description: Student's age in years
required: true
- field: gender
type: string
enum: [Male, Female, Non-binary, "Prefer not to say"]
example: Female
description: Self-reported gender identity
required: true
- field: ethnicity
type: string
example: Hispanic
description: Student's self-identified ethnic or racial background
required: false
household:
- field: address_type
type: string
enum: [Urban, Rural, Suburban]
example: Urban
description: Type of residential area
required: true
- field: family_size
type: integer
min: 1
max: 20
example: 4
description: Total number of people in the household
required: true
- field: num_siblings
type: integer
min: 0
example: 2
description: Number of siblings (including half/step siblings)
required: true
- field: birth_order
type: integer
min: 1
example: 1
description: Birth order (1 = firstborn, 2 = second child, etc.)
required: true
family_background:
structure:
- field: parent_marital_status
type: string
enum: [Single, Married, Separated, Divorced, Widowed, "Domestic Partnership"]
example: Married
description: Current marital/relationship status of parents/guardians
required: true
- field: guardian
type: string
enum: ["Father", "Mother", "Parents", "Grandparent", "Other Relative", "Foster Care"]
example: Parents
description: Primary guardian(s) the student lives with
required: true
education:
- field: mother_education
type: integer
enum: [0, 1, 2, 3, 4]
example: 3
description: |
0 = No formal education
1 = Primary education
2 = Secondary education
3 = Some college/technical school
4 = Bachelor's degree or higher
required: true
- field: father_education
type: integer
enum: [0, 1, 2, 3, 4]
example: 3
description: |
0 = No formal education
1 = Primary education
2 = Secondary education
3 = Some college/technical school
4 = Bachelor's degree or higher
required: true
employment:
- field: mother_occupation
type: string
example: "Registered Nurse"
description: Mother's current or most recent occupation
required: false
- field: father_occupation
type: string
example: "Software Engineer"
description: Father's current or most recent occupation
required: false
resources:
- field: internet_access
type: boolean
example: true
description: Whether the student has reliable internet access at home
required: true
- field: family_support
type: boolean
example: true
description: Whether family provides academic and emotional support
required: true
- field: family_history_mental_health
type: boolean
example: false
description: Whether there is a known family history of mental health conditions
required: true
academic_profile:
# Core identification and enrollment information
identification:
- field: student_id
type: string
format: UUID
example: "550e8400-e29b-41d4-a716-446655440000"
description: Unique identifier for the student in the system
required: true
- field: school_id
type: string
pattern: '^[A-Z]\d{3}$'
example: "S123"
description: "Unique identifier for the educational institution"
required: true
academic_status:
- field: enrollment_year
type: integer
min: 2000
max: 2100
example: 2023
description: Year the student first enrolled at the institution
required: true
- field: current_year
type: integer
min: 2000
max: 2100
example: 2025
description: Current academic year
required: true
- field: class_standing
type: string
enum: ["Freshman", "Sophomore", "Junior", "Senior", "Graduate"]
example: "Junior"
description: Current academic standing based on credit hours completed
required: true
academic_performance:
gpa:
- field: cumulative_gpa
type: float
min: 0.0
max: 4.0
example: 3.75
description: Cumulative Grade Point Average on a 4.0 scale
required: true
- field: current_term_gpa
type: float
min: 0.0
max: 4.0
example: 3.9
description: GPA for the current academic term
required: true
standardized_scores:
- field: math_score
type: integer
min: 0
max: 100
example: 88
description: Most recent mathematics examination score (0-100)
- field: language_arts_score
type: integer
min: 0
max: 100
example: 92
description: Most recent language arts examination score (0-100)
- field: science_score
type: integer
min: 0
max: 100
example: 85
description: Most recent science examination score (0-100)
- field: social_studies_score
type: integer
min: 0
max: 100
example: 90
description: Most recent social studies examination score (0-100)
- field: foreign_language_score
type: integer
min: 0
max: 100
example: 82
description: Most recent foreign language examination score (0-100)
performance_metrics:
- field: academic_failures
type: integer
min: 0
example: 1
description: Total number of failed courses to date
required: true
- field: academic_probation
type: boolean
example: false
description: Whether the student is currently on academic probation
required: true
academic_engagement:
preparation:
- field: test_preparation_completed
type: boolean
example: true
description: Whether the student has completed a test preparation course
required: true
- field: study_hours_weekly
type: integer
min: 0
max: 100
example: 15
description: Average number of hours spent studying per week
required: true
self_assessment:
- field: academic_pressure_level
type: integer
min: 1
max: 5
example: 3
description: Self-reported level of academic pressure (1=Very Low, 5=Very High)
required: true
- field: study_time
type: integer
min: 0
max: 40
required: true
example: 20
description: Weekly hours spent studying
# Extracurricular involvement details
- field: extracurricular_participation
type: object
required: true
properties:
- field: is_active
type: boolean
required: true
example: true
description: Whether the student participates in any extracurricular activities
- field: weekly_hours
type: number
minimum: 0
maximum: 40
required: true
example: 5.5
description: Average weekly hours spent on extracurricular activities
- field: activity_types
type: array
items:
type: string
enum: [sports, academic_clubs, arts, community_service, leadership, other]
required: true
example: ["sports", "academic_clubs"]
description: |
Types of activities the student participates in:
- sports: Team or individual sports
- academic_clubs: Math club, science club, debate, etc.
- arts: Music, theater, visual arts
- community_service: Volunteer work, charity organizations
- leadership: Student government, peer mentoring
- other: Any activities not covered above
- field: leadership_roles
type: array
items:
type: string
required: false
example: ["team_captain", "club_president"]
description: Any leadership positions held in these activities
# Athletic participation details
- field: athletic_involvement
type: object
required: true
properties:
- field: is_active
type: boolean
required: true
example: true
description: Whether the student currently participates in any athletic activities
- field: sports
type: array
items:
type: string
enum: [soccer, basketball, volleyball, track_field, swimming, tennis, baseball, football, other]
required: true
example: ["basketball", "track_field"]
description: |
List of sports the student participates in:
- soccer: Association football
- basketball: Basketball
- volleyball: Volleyball
- track_field: Track and field athletics
- swimming: Competitive swimming
- tennis: Tennis
- baseball: Baseball or softball
- football: American football
- other: Any sport not listed above
- field: competition_level
type: string
enum: [intramural, junior_varsity, varsity, club, recreational]
required: false
example: "varsity"
description: |
Highest level of competition:
- intramural: School intramural leagues
- junior_varsity: School JV team
- varsity: School varsity team
- club: Competitive club teams
- recreational: Non-competitive/recreational play
- field: weekly_hours
type: number
minimum: 0
maximum: 40
required: true
example: 8.5
description: Average weekly hours spent on athletic activities including practice and games
- field: positions
type: array
items:
type: string
required: false
example: ["point_guard", "shooting_guard"]
description: Positions played in team sports (if applicable)
- field: awards
type: array
items:
type: string
required: false
example: ["mvp_2024", "all_conference"]
description: Athletic achievements or recognitions received
# Career and work-related information
- field: has_part_time_job
type: boolean
required: true
example: false
description: |
Indicates if the student is currently employed in a part-time position.
Includes both formal employment and informal work arrangements.
- field: work_hours_weekly
type: integer
min: 0
max: 40
required: true
example: 10
description: |
Average number of hours worked per week in part-time employment.
Set to 0 if not currently employed.
# Higher education and career aspirations
- field: higher_education_intent
type: string
enum: ["definitely_yes", "likely_yes", "unsure", "likely_no", "definitely_no"]
required: true
example: "likely_yes"
description: |
Student's current intention to pursue higher education after high school.
This helps in academic counseling and resource allocation.
- field: career_field_interest
type: string
required: false
example: "computer_science"
description: |
Broad field of career interest. Can be used to connect students with
relevant opportunities and resources. Examples include:
- computer_science
- healthcare
- business
- engineering
- arts_humanities
- education
- undecided
- field: career_confidence
type: integer
min: 1
max: 5
required: true
example: 4
description: |
Student's confidence level in their career choice (1-5):
1: Not at all confident
2: Slightly confident
3: Moderately confident
4: Very confident
5: Extremely confident
# Personal relationships
- field: has_romantic_relationship
type: boolean
required: true
example: false
description: |
Whether the student is currently in a romantic relationship.
Used to understand social support systems and time commitments.
# Academic and work engagement
- field: academic_engagement
type: integer
min: 1
max: 5
required: true
example: 4
description: |
Self-reported level of engagement with academic work (1-5):
1: Very disengaged
2: Somewhat disengaged
3: Neutral
4: Somewhat engaged
5: Very engaged
# Attendance and school commute information
attendance:
- field: attendance_record
type: object
required: true
properties:
- field: total_absences
type: integer
minimum: 0
maximum: 365
required: true
example: 5
description: Total number of school days missed in the current academic year
- field: excused_absences
type: integer
minimum: 0
maximum: 365
required: true
example: 2
description: Number of absences with valid excuse (included in total_absences)
- field: tardies
type: integer
minimum: 0
maximum: 200
required: true
example: 3
description: Number of late arrivals to school
- field: attendance_rate
type: number
minimum: 0
maximum: 100
required: true
example: 95.5
description: Percentage of school days attended (0-100%)
- field: transportation_details
type: object
required: true
properties:
- field: primary_transport
type: string
required: true
enum: [school_bus, public_transit, family_vehicle, carpool, walking, bicycle, other]
example: "school_bus"
description: |
Primary mode of transportation to school:
- school_bus: District-provided school bus
- public_transit: Public transportation (metro, city bus, etc.)
- family_vehicle: Personal/family car
- carpool: Shared ride with other students
- walking: Walking to school
- bicycle: Biking to school
- other: Other transportation method
- field: secondary_transport
type: string
required: false
enum: [school_bus, public_transit, family_vehicle, carpool, walking, bicycle, none]
example: "family_vehicle"
description: Secondary/backup transportation method, if any
- field: average_commute_time
type: object
required: true
properties:
- field: minutes
type: number
minimum: 0
maximum: 240
required: true
example: 22.5
description: Average one-way commute time in minutes
- field: consistency
type: string
enum: [very_consistent, somewhat_consistent, variable, unpredictable]
required: true
example: "somewhat_consistent"
description: |
How consistent the commute time is:
- very_consistent: ±5 minutes
- somewhat_consistent: ±15 minutes
- variable: ±30 minutes
- unpredictable: Varies by more than 30 minutes
- field: has_transportation_issues
type: boolean
required: true
example: false
description: Whether the student experiences frequent transportation problems
mental_health:
# Self-reported mental health conditions and symptoms
conditions:
- field: depression_diagnosis
type: boolean
example: true
description: Whether the student has been diagnosed with depression by a professional
required: true
- field: depression_severity
type: integer
min: 0
max: 10
example: 6
description: Self-reported depression severity (0=None, 10=Extreme)
required: true
- field: anxiety_diagnosis
type: boolean
example: true
description: Whether the student has been diagnosed with an anxiety disorder
required: true
- field: anxiety_severity
type: integer
min: 0
max: 10
example: 7
description: Self-reported anxiety severity (0=None, 10=Extreme)
required: true
- field: panic_attack_frequency
type: string
enum: ["Never", "Rarely", "Monthly", "Weekly", "Daily"]
example: "Monthly"
description: Frequency of panic attacks experienced
required: true
risk_factors:
- field: suicidal_ideation
type: boolean
example: false
description: Whether the student has experienced thoughts of self-harm or suicide
required: true
severity: high_risk
- field: self_harm_behavior
type: string
enum: ["Never", "In the past", "Currently"]
example: "In the past"
description: History of self-harm behaviors
required: true
severity: high_risk
- field: substance_use_frequency
type: string
enum: ["Never", "Rarely", "Monthly", "Weekly", "Daily"]
example: "Rarely"
description: Frequency of alcohol or drug use
required: true
behavioral_indicators:
- field: social_isolation
type: integer
min: 1
max: 5
example: 3
description: Self-reported level of social isolation (1=Not at all, 5=Extremely)
required: true
- field: mood_instability
type: integer
min: 1
max: 5
example: 3
description: Frequency of mood swings (1=Never, 5=Constantly)
required: true
- field: stress_level
type: integer
min: 1
max: 10
example: 7
description: Current stress level (1=None, 10=Extreme)
required: true
- field: coping_effectiveness
type: integer
min: 1
max: 5
example: 3
description: Self-rated effectiveness of coping strategies (1=Not at all, 5=Very)
required: true
support_system:
- field: counseling_usage
type: string
enum: ["Never", "In the past", "Currently"]
example: "Currently"
description: History of using counseling services
required: true
- field: medication_usage
type: string
enum: ["None", "In the past", "Currently prescribed"]
example: "Currently prescribed"
description: Current or past psychiatric medication use
required: true
- field: social_support_quality
type: integer
min: 1
max: 5
example: 4
description: Perceived quality of social support (1=Very poor, 5=Excellent)
required: true
wellbeing_metrics:
# Daily health and wellness behaviors
lifestyle:
- field: sleep_hours
type: float
min: 0
max: 24
example: 6.5
description: Average nightly sleep duration in hours
required: true
- field: screen_time_hours
type: float
min: 0
max: 24
example: 4.5
description: Average daily recreational screen time in hours
required: true
- field: physical_activity_hours
type: float
min: 0
max: 168
example: 3.0
description: Weekly exercise time in hours
required: true
# Standardized psychological assessments
survey_scores:
- field: PHQ9_score
type: integer
min: 0
max: 27
example: 8
description: |
PHQ-9 Depression Severity Score (0-27):
0-4: Minimal depression
5-9: Mild depression
10-14: Moderate depression
15-19: Moderately severe depression
20-27: Severe depression
required: true
- field: WHO5_score
type: integer
min: 0
max: 25
example: 15
description: |
WHO-5 Well-Being Index (0-25):
0-12: Low well-being
13-17: Moderate well-being
18-25: High well-being
required: true
- field: GAD7_score
type: integer
min: 0
max: 21
example: 6
description: |
GAD-7 Anxiety Severity Score (0-21):
0-4: Minimal anxiety
5-9: Mild anxiety
10-14: Moderate anxiety
15-21: Severe anxiety
required: true
- field: PSS_score
type: integer
min: 0
max: 40
example: 16
description: |
Perceived Stress Scale (0-40):
0-13: Low stress
14-26: Moderate stress
27-40: High stress
required: true
- field: UCLA_loneliness_score
type: integer
min: 20
max: 80
example: 45
description: |
UCLA Loneliness Scale (20-80):
20-34: Low loneliness
35-49: Moderate loneliness
50-80: High loneliness
required: true
# Text analysis metrics
sentiment_analysis:
- field: sentiment_compound
type: float
min: -1.0
max: 1.0
example: 0.5
description: |
Overall sentiment polarity (-1.0 to +1.0):
-1.0 to -0.5: Very negative
-0.5 to -0.1: Negative
-0.1 to 0.1: Neutral
0.1 to 0.5: Positive
0.5 to 1.0: Very positive
required: true
- field: sentiment_positive
type: float
min: 0
max: 1
example: 0.4
description: Proportion of positive sentiment (0-1)
required: true
- field: sentiment_neutral
type: float
min: 0
max: 1
example: 0.3
description: Proportion of neutral sentiment (0-1)
required: true
- field: sentiment_negative
type: float
min: 0
max: 1
example: 0.3
description: Proportion of negative sentiment (0-1)
required: true
# Readability metrics
readability_scores:
- field: ARI
type: float
min: 1
max: 20
example: 7.5
description: Automated Readability Index (1-20, higher is more complex)
required: true
- field: Coleman_Liau_Index
type: float
min: 1
max: 20
example: 8.2
description: Coleman-Liau readability score (1-20, higher is more complex)
required: true
- field: Flesch_Kincaid_Grade_Level
type: float
min: 1
max: 16
example: 9.1
description: U.S. school grade level needed to understand the text (1-16)
required: true
# System and administrative metadata
meta:
# Timestamp information
- field: created_at
type: datetime
format: date-time
example: "2025-08-17T14:33:00-04:00"
description: |
ISO 8601 timestamp when this record was first created.
Always include timezone offset (e.g., -04:00 for EDT).
required: true
- field: updated_at
type: datetime
format: date-time
example: "2025-08-17T14:33:00-04:00"
description: |
ISO 8601 timestamp when this record was last modified.
Should match created_at for new records.
required: true
# Data source and versioning
- field: data_source
type: string
example: "student_portal_v1"
description: |
Identifier for the system or interface that collected this data.
Should be a URL-friendly string (lowercase, underscores).
required: true
- field: schema_version
type: string
pattern: '^\d+\.\d+\.\d+$'
example: "1.0.0"
description: |
Version of the schema this data conforms to.
Follows semantic versioning (MAJOR.MINOR.PATCH).
required: true
# Data quality flags
- field: is_complete
type: boolean
example: true
description: |
Indicates whether all required fields have been populated.
Should be false if any required fields are missing.
required: true
- field: data_quality_score
type: integer
min: 0
max: 100
example: 95
description: |
Automated data quality assessment score (0-100).
Higher values indicate better data quality.
required: true
Early Signal Project 