Axis Bank AI Challenge

3740 Registered Allowed team size: 1 - 5

Winners are announced.

idea phase
starts on:
Sep 12, 2018, 02:30 PM
ends on:
Oct 28, 2018, 06:25 PM
starts on:
Nov 06, 2018, 07:30 AM
ends on:
Dec 03, 2018, 06:25 PM



To view the shortlisted teams, please click here

Axis Bank is one of the first new generation private sector banks to have begun operations in 1994.

Today it the third largest bank of the country, providing a wide spectrum of financial services to multiple customer segments – Retail, SME, Agri & Corporate.

Axis has always been forward in technology adoption and using tech in the creation of customer-centric products & services. This Hackathon is an initiative by Axis Bank to promote innovation in the country and help Startups/Developers and Student entrepreneurs to think out of the box and come up with great solutions for the bank. Purpose of this hackathon is to identify the talent and engage with them for co-learning and co-creating tech & business applications in a collaborative and fun way.

Format & Hackathon Phases:

The Hackathon will be divided into 3 phases. Each phase will have an elimination round.

Phase I - Ideation: September 12th to October 28th

In this phase, we want to learn about your approach towards building a solution for the chosen problem/problems. Briefly describe:

  • Solution Design
  • Tech Stack, you will be using (You cannot use any published APIs)
  • Algorithms/Models you will be using

You don’t have to implement exactly what you describe in this phase. We understand that your approach, design, chosen stack, and methodology may change when you will start building the solution. This deliverable is to gauge your understanding of the problem and guide you towards the building of the right solution.

Shortlist announcement date: 4th November

Phase II: Prototype Development: November 5th to December 2nd

In this phase, your deliverable is a working prototype solution for the problem chosen. We shall provide you with training data sets. Teams may either submit their work via their GitHub repository links or via uploading zipped folders, along with instructions for the creation of execution environment and running the solution. The solutions will be executed and judged for their accuracy and experience.

Besides, you need to submit a write-up covering:

  • Final solution design
  • Algorithm/Models actually applied
  • Tech stack used
  • Accuracy attained
  • Any deviations
  • As an output, the system should return the table content in an excel format, same as the data sets for table recognition.

Shortlist announcement date: 8th December

Phase III: Finale at Thought Factory Office, Bangalore: December 15th to 16th

For the finale, you shall be invited to Axis Bank’s Innovation Lab, Thought Factory, for a 24-hour exciting hack. You will be accompanied by Bank’s tech leaders & data scientists in the final refining of your solution. The final solutions, on submission, will be executed by our mentors and judged for accuracy, scope coverage, usability, experience, and novelty.

Finalists shall get an opportunity to present and talk about their solutions before the senior-most management of the Bank.


Signature Recognition

A person’s signature is a representative of his identity. For us at the Bank, a signed document by a customer is an instruction from him for carrying out an approved transaction for him.

On on-boarding a customer we capture an image of his signature in our systems, and on receiving a signed document (Cheques, DDs and others) from him we match the signature on the document with the one recorded in the database before proceeding with the instruction.

In the case of skilled forgeries, it becomes very difficult to verify the identity of the customer.

We want you to build a system that can help us distinguish forgeries from actual signatures. This system should be able to study signature parameters as strokes, curves, dots, dashes, writing fluidity & style, in a Writer-Independent manner and create features for identification of the signature.

The system should not use any existing APIs and should be completely self-developed.

How should it work?

The system shall work in 2 steps:

  • Step 1: Accept & Store Genuine Signature Image: Take actual signature scanned image of the on-boarding customer and store it in a database against a unique Customer ID
  • Step 2: Accept & Compare Signature Images: Accept inputs of Customer ID, and corresponding signature image. Compare with the signature stored in DB against the given Customer ID, and return a Confidence Match Score between the two signature images

Download Sample Datasets

Table Reading & Understanding in Documents/Images

With advent of AI-RPA, document reading and analysis are on their way for becoming mainstream. Tables in documents help represent information in a structured way. For a comprehensive document analysis, it is important to be able to identify, read and understand tables present in documents. This step, although despite a successful OCR, may become difficult, as tables vary a lot in their layout, formats and encoding.

The problem at hand is to build a solution that can detect tables in given documents, then make sense of the information they present.

For this problem too, you cannot use any existing APIs.

How should the system work?

  • Step 1: Accept document input, read tables: System should have an input mechanism for accepting documents (PDFs, MSWord) or document images (TIFF, JPEG). The document may have one or more tables.
  • Step 2: Step 2: As an output, system should return the table content in an excel format,same as that in the sample data sets
    Download Sample Datasets

Prizes INR 5,00,000 in prizes

Apart from the prize money, participants will get:

  • POC opportunities with Bank for start-ups.
  • Internship opportunities for students.
  • 1-month free space for 4 member team at Axis Social
Main Prizes
First Prize
INR 2,50,000
Second Prize
INR 1,50,000
Third Prize
INR 1,00,000

Social Share

View All Notifications