1

Reduce manual verification effort for teachers

2

Avoid proxy (voice impersonation by students)

3

Increase academic interaction time b/w students & teachers

What do we want to acheive ?

What do we want to acheive ?

OBJECTIVE

How to save time

doing administrative tasks

Marking attendance of a large student group with AI

Attendance by Live Class Photographs

Attendance by Live Class Photographs

THE SOLUTION

By Teacher

5 mins

Voice Impersonation

Proxy

VERIFY MANUALLY

Old Way

By AI (Facial Recognition)

< 1 min

No Voice Impersonation

No Proxy

VERIFIED AUTOMATICALLY

New Way

While it’s clear that AI outcomes aren't 100% accurate, what we can achieve is a substantial reduction in manual work through AI integration. Teachers nevertheless have the flexibility to change the attendance status of the student.

But, why is the student face zoomed in after detection ?

Manual marking of attendance displays student cards with profile images taken during enrollment. Arivoo's AI matches student faces against stored images in the database & captures only the essential facial features for display on the user interface card.

How - By Face Embedding Extraction…

TEST RUN ON ADAMAS UNIVERSITY STUDENTS

Live Frame

Human Face Identified

Ready for Embedding Extraction

Extracted

Embeddings matched

Present Detected

ANNOTATED FRAME

Process Summary

HIGH LEVEL

It is a process of adding labels or descriptive information to train a computer vision model.

By Annotation

It is a process of adding labels or descriptive information to train a computer vision model.

By Annotation

Okay, Let's talk about design :)

Okay, Let's talk about design :)

Adamas Tech is an international Ed-Tech brand that focuses on teachers & students to chase mastery. As of now, it has expanded to providing AI based solutions for schools, universities & learning management.

Project Overview

Project Overview

This project highlights how design helped teachers save 10% percent from the class time marking student attendance and increasing top of the funnel.

What

Product Design, UX copy writing, strategy & user testing

My Role

UX researcher, product manager & software developers

Collaboration with

Why are we re-designing ?

Why are we re-designing ?

BACKSTORY

Manual attendance marking wasted a lot of time of the teacher. Considering that a few students don’t cooperate, it again takes a toll on the teacher wasting some percentage of the total class time losing an overall 97 hours annually.

Here along with marketing and sales campaigns, design can help optimise these numbers. This particular feature played an instrumental role in saving attendance marking time and further optimising the live class funnel.

2 AI Engineers, 2 Backend devs (for APIs), 2 Frontend devs.

Types

7

2 AI Engineers, 2 Backend devs (for APIs), 2 Frontend devs.

Types

7

How to avoid giving proxy or fake attendance ?

How to avoid giving proxy or fake attendance ?

LIVE CLASS ATTENDANCE MARKING FUNNEL OPTIMISATION

Mark attendance

By Image

Manual

Submit

or

PRIMARY

The Problem Statement

Many times between the student roll calls, a few student helps other students get proxy either by impersonating their voice or by requesting the person who's marking attendance on teacher's behalf.

Voice impersonation

Invalid attendance report

Student roll calls

Existing Flow

New Flow

But, how do we flag invalid students ?

A lot of times, students from another class come and sit in their friend’s class. Those are the
students which the system filters and informs the teacher about them.

Arivoo's AI

Matches live frames with database images

Flags invalid students

What after we went live after 28 days…

In case of similar faces found after uploading class photographs, one student was identified as another student from a different photograph identifying the latter student as present (actually absent).

Wrong attendance

Trust issues

Similar faces

Give Present/Absent

Submit

Fake Attendance

PROXY

By Image

Manual

Facial Recognition

Invalid Students Filtered

or

2/2

What can be improved ?

What can be improved ?

PROBLEM STATEMENT

8-10% of the total class time was wasted in marking student attendance. The reason varies
in different steps of the process and is being discussed in the respective user flows mentioned below. However, some of the generic problems are -

Manual Verification

Proxy

Speed

If class was dedicated 60 mins, then 5-6 mins were wasted in manual attendance marking considering that a few students were not cooperating with the teacher giving response to the roll calls.

Problem Discovery Methods

Problem Discovery Methods

Deep learning of real-time metrics

& hypothesis

Quantitative Data

Gathering user perspectives &

pain points

User Calling

From inception to execution

From inception to execution

VISION

The vision was to learn from quick experimentation and rapid testing with users to offer the best digital attendance marking experience to them.

Rapid Testing

Quick Optimising

*Roughly (2 months)

Who should care ?

Who should care ?

THE USERS

Academic Staff

Works in a university

Our primary target audience has the similar needs as this persona -

Hi, I'm Dr. Sriya

A professor aged 29 years at Adamas University. I oversee the electronics and communication department within the institution.

Why quick attendance ?

I need to dedicate maximum time interacting withthe students. A couple of students don’t cooperate with me while I mark attendance hence wasting a lot of dedicated class time.

I want

  • to save time marking attendance

    for a large student group



  • to avoid giving proxy



  • a digital and quick way

Current attendance marking process

Current attendance marking process

Student Call Outs

Verify Manually

Give Present/Absent

Submit

How to reduce manual verification effort
for teachers ?

How to reduce manual verification effort
for teachers ?

1/2

We introduced an entirely new real estate to pitch marking attendance by uploading class photographs from their mobile. Core JTBD of this method is to open the device (mobile or tablet) camera and upload class photographs.

We introduced an entirely new real estate to pitch marking attendance by uploading class photographs from their mobile. Core JTBD of this method is to open the device (mobile or tablet) camera and upload class photographs.

New - Mark attendance with class photograph

What if users gets a primary option to mark attendance by uploading class photographs instead of manually giving them present or absent status.

Upload class photo

Quick attendance

Tap to upload a class photograph

Primary action

Educate the user about the new process

How

User can skip to manual (old) way to mark attendance also

Skip (secondary action)

New Entry Point

Old Way

How to reduce drop off rate from 31% ?

To reduce the drop off rate, we optimised the user flow in following 3 layers:

1

Adding a dedicated benefits page

2

Defining strict image acceptance criterion

System Efficiency

3

Alert for similar faces

Risk Management

Winning Trust

Funnel 1 - Winning Trust

Funnel 1 - Winning Trust

ADDING A DEDICATED BENEFITS PAGE

Solving for trust

Distrust comes from unfamiliar things. Here user’s concern would be ‘What if the new attendance marking process is not accurate enough, do I again have to recheck manually ?’

How did we address this issue ?

Transparency

Clear Communication

Validation

What is the new process

How does it work & benefits

Social proofs for inefficiency

OLD PAGE

FEEDBACK

The existing ‘How does it work’ section was inferred as a distracting estate for the teachers. Also, once the teacher get’s familiar with the process, this section becomes obsolete and of no value.

EXPERIMENT

We introduced an entire new page for the benefits of quick attendance, keeping the existing page focused on just uploading class photo.

NEW PAGE

The core USP : Mark attendance of the large student group within seconds

What

Dedicate only upto 2% of the total
class time marking student attendance

Outcome

A self explanatory process for quick attendance : Capture, upload and wait for a few secs

How ?

Mentioning the benefits to make
teacher realise how efficient is this way of marking student attendance

Why ?

Winning trust of the teachers by showing social proofs & making them realise the actual need for quick attendance.

Need

Bottom sheets - Benefit cards

SECONDARY LINK TO GO & MARK ATTENDANCE

Funnel 2 - System Efficiency

Funnel 2 - System Efficiency

STRICT CRITERION FOR IMAGE UPLOAD

Poor Image Quality

Improper Lighting

Obstructed Faces

Image rejection use case

If the system doesn’t accept the image, user still has an option to skip and give manual attendance.

CONTROL

CASE 1

CASE 2

CASE 3

CASE 4

Not accepted

Accepted

Image acceptance use case

Once an image gets accepted by the system, the focus shifts to ‘proceed’ keeping in mind that
user might want to add more images as well.

But, how does the images get processed ?

Schedule a meeting and I'll answer all your questions.

aman.vermaproduct@gmail.com

Funnel 3 - Alert for Similar Faces

Funnel 3 - Alert for Similar Faces

RISK MANAGEMENT

Wrong attendance

Trust issues

Invalid report

Opportunity

  • The similar faces will be flagged to the teacher before providing the recognised student list.

  • The teacher will manually confirm if the student is actually present or not.

1/3 - Upload

EXISTING

2/3 - Similar Faces Found

NEW

3/3 - Students Recognised

EXISTING

Challenges in User Experience

The teacher has an option to upload multiple images. A student was recognised as another student due to a different angle, lighting, or any other external factor in the other image identifying the latter student as present which was wrong,

Happy Flow - Quick Attendance by AI

Happy Flow - Quick Attendance by AI

NEW HASSLE-FREE EXPERIENCE

< 1 min

Comprehensive error handling

Reduced no. of clicks

1/6

Start

2/6

Captures

3/6

Captures again

4/6

Proceeds

Waits

5/6 (Less Chance)

Manual Check

6/6

Submits

Scroll Left to see the happy flow

Is the quick attendance funnel really optimised ?

Is the quick attendance funnel really optimised ?

These are the max no. of taps user has to do considering the edge cases as well.

The complete live class attendance marking funnel gave results within a minute unlike the manual process which took around 6 mins depending upon the student strength.

Dashboard - Masthead States

COMPLETED

COMPLETED

COMPLETED

COMPLETED

Overall Business Impact

Overall Business Impact

+8%

More time for student interaction

0%

Proxy

(fake attendance)

Some of the high level but impactful metrics from this data driven design project.

LIVE

LIVE

6 Taps

Where did we win ?

Time

Online

UPCOMING

UPCOMING

Offline w/ Location