Storage notice

We only use technically necessary browser storage (localStorage) to keep you logged in and remember your settings. No cookies, no tracking, no analytics. More in our Privacy Policy.

Technical Deep Dive

The science behind every session

StudiPace isn't a todo list with a timer. It's a multi-layered optimization engine built on decades of cognitive science research — fully automated, continuously adapting.

studipace.app

Schedule

12 sessions540 min
↻ Regenerate
+ Add
Mon 14
Tue 15
Wed 16
Thu 17
Fri 18
Sat 19
Sun 20
08:00
Math
Math
English
09:00
Physics
Physics
10:00
Physics
Math
11:00
Bio
Bio
12:00
Bio
13:00
English
14:00
Math
15:00
16:00
17:00

Upcoming Exams

Biology Exam8d
45% ready
Physics Final18d
88% ready
English Essay5d
60% ready

Research Foundations

Four pillars from cognitive science

Every scheduling decision is grounded in peer-reviewed research on how human memory encodes, stores, and retrieves information.

What is the science behind StudiPace? How does spaced repetition improve exam results?

Spaced Repetition

Sessions are distributed across time at increasing intervals, matching the forgetting curve discovered by Ebbinghaus (1885). This alone can improve retention by 200% compared to massed practice.

Ebbinghaus, H. (1885). Memory: A Contribution to Experimental Psychology.

Retrieval Practice

The testing effect shows that actively recalling information strengthens memory traces far more effectively than passive re-reading. Our system schedules retrieval-focused sessions at optimal intervals.

Roediger & Butler (2011). The critical role of retrieval practice in long-term retention.

Interleaving

Mixing different subjects and topics within study blocks forces the brain to discriminate between problem types, leading to deeper encoding and better transfer to exam conditions.

Rohrer & Taylor (2007). The shuffling of mathematics problems improves learning.

Desirable Difficulty

Study sessions are placed at the point where material is challenging but not impossible to recall — the sweet spot where learning is maximized according to Bjork's framework.

Bjork, R.A. (1994). Memory and Metamemory Considerations.

The Engine

Multi-layered penalty optimization

How does StudiPace decide when to schedule each study session?

Instead of simple rule-based scheduling, StudiPace scores every possible placement through four independent penalty dimensions. The lowest combined penalty wins.

total = day + subject + timeslot + epoch

Day Penalties

Scores each calendar day based on distance to exam, existing load, rest days, and overall schedule density.

Subject Penalties

Ensures balanced coverage across all subjects. Penalizes over-concentration on one subject.

Timeslot Penalties

Evaluates each hour against your availability, cognitive load patterns, and commitments.

Epoch Penalties

Enforces spaced repetition intervals, preventing session clustering across weeks.

Greedy placement with re-scoring

Each session is placed at the minimum-penalty slot, then all affected slots are re-scored before the next placement — accounting for cascading effects.

Penalty Heatmap

Placing: Mathematics — 45 min

Low
Med
High
Mon
Tue
Wed
Thu
Fri
Sat
Sun
08:00
12
18
45
30
8
99
65
09:00
22
5
BEST
38
25
15
88
70
10:00
35
28
10
42
20
75
55
11:00
40
32
50
15
30
60
80
14:00
8
20
35
28
12
70
90
15:00
15
10
25
35
18
55
45
16:00
30
22
40
20
25
Optimal placement: Tuesday 09:00 — penalty score: 5

Readiness Model

Four-dimensional exam readiness

How do I know if I'm ready for my exam?

A composite score that tells you — and the algorithm — exactly how prepared you are for each exam, across four weighted dimensions.

Exam Readiness

Physics Final

18 days remaining

76%ready
Coverage55% weight
72%
Spacing20% weight
85%
Quality15% weight
68%
Retention10% weight
91%
readiness = 0.55·coverage + 0.20·spacing + 0.15·quality + 0.10·retention
studipace.app

Good afternoon, Alex

Thursday, 17 April

90 min left🔥 10
Up Next

Physics

45 min·14:00·Wave mechanics
Readiness impact
68%74%+6%
Coverage
63%
Spacing
74%
Quality
70%
Retention
83%

Timeline

Mathematics
09:00 – 09:45
Biology
11:30 – 12:00
NOW · 13:42
Physics
14:00 – 14:45
English
16:30 – 17:00

ML-Personalized Weights

The default weights (55/20/15/10) are based on research averages. Over time, the student profile ML weight learner adjusts these ratios to match your individual learning patterns — some students benefit more from spacing, others from coverage depth.

The Pipeline

From data to optimized schedule

What happens in the seconds between clicking "generate" and seeing your plan.

1

Data Ingestion

Subjects, exams, topics, availability windows, weekly activities, and timetable are loaded.

2

Penalty Scoring

Every possible (day, timeslot, subject) combination is scored through 4 independent penalty layers.

3

Session Placement

The session placer greedily selects the lowest-penalty slot, places a session, and re-scores affected slots.

4

Readiness Validation

The readiness model verifies sufficient coverage, spacing, quality, and retention.

5

ML Personalization

The weight learner adjusts readiness dimensions based on the student's historical data.

Experience the algorithm yourself

The best way to understand the system is to use it. Create a free account, add your first exam, and watch the penalty engine work.