As the famous Japanese proverb states, “Better than a thousand days of diligent study is one day with a great teacher.” I was raised by a great teacher. My father taught primary school for 25 years and was truly beloved by his students. There is dedication, responsibility, and a focus on details in everything he does. It isn’t surprising that it is these qualities that has made me successful in my life. I’m Pooja Bhandarkar, Team Lead, Quality Assurance at Blanc Labs and this is my story.

I grew up in a small town in the Southern part of India, called Udupi. Today, Udupi is a thriving metropolis known for its trademark cuisine, educational institutions and historical sites. When I was growing up, it still had the charm of a small town and provided the perfect environment for my childhood.

The focus at our home was heavily on academics. My father would tell me to study, get a degree and then chase my goals. I realized very early on that I wanted to be an engineer one day. The action of putting together various elements to create a complete entity was fascinating to me.

My introduction to Quality Assurance

After graduating with a degree in computer science engineering at PES University, an institution on the forefront of technology education and research, I worked as a Quality Assurance (QA) Specialist for a company in India. The role of a QA specialist is to ensure that the product, at every stage of its development and presentation to the client complies with the company’s quality standards. I found myself adept at finding as many issues in the product as possible and it gave me tremendous satisfaction in knowing that my review helped my team succeed in delivering the best viable product to the client.

After four years of being a QA Specialist in India, I made the bold and exciting move of immigrating to Canada. This transition was not entirely seamless. Navigating the job market was challenging for a new entrant such as myself – the cultural nuances through the interview process in itself was a factor. But in November 2019, I found Blanc Labs and joined the team. I was drawn to the sector and the tech mindset, which was very forward thinking. I had never been in such an agile company going through a rapid scale up before. The entrepreneurial culture imparted a growth mindset in me, and I was excited to explore that, and the ability to create more impact on the overall performance of the company.  

Exciting new challenges

Taking a deeper dive into my responsibilities as QA Specialist, I had to check the application (built by the developers) against the client’s requirements (provided to me by the business analyst), ensuring there are no gaps/issues with functionality built. Though this seems straight forward, at the time, the developer to QA ratio was 10:1 (a more normalized number being 3:1). In addition, I had to learn the commercial lending process and delivery quality very quickly.

Always the eager student, I took it upon myself to learn as much as I could about the requirements, the stories, the questions, and the testing at very sprint. I am proud to say we saw no delays on any projects or deliveries.

The other challenge that I faced was my perception of the client. I’d always been taught to see the client as an entity that is superior to the company I represented. Their word was law and their needs and wants superseded my opinions. At Blanc Labs, we are completely collaborative with our clients in every project. My manager and mentor taught me that hierarchy should never get in the way of project delivery and success. Our clients are open and receptive to our insights and with that, I have been able to partner with them more effectively.

What does it take to succeed?

Today, I am proud to share I have grown to lead a team of QA Specialists. When I think about what it takes to be effective at what I do, it boils down to these things:

• Become an eternal student: You have to understand the goal and recognize the outcome. You have to know the application in and which helps the process easier.
• Stay focused: The quality of an application depends on you and so you need to be attentive to find every issue/ gap and ensure that the product is functioning and delivering in the way the client requires.
• Agile delivery: With agile, QA is brought in early in the process to uncover any gaps, adding more focus to more effective delivery.
• Demonstrate leadership: Irrespective of whether I was an individual contributor, or now, where I lead a team of QA specialists, I always take a leadership approach by establishing a foundation of standard practices across all projects, and encouraging those around me to learn and adapt to new tools, for example, to focus more on automation testing, which helps to improve test coverage.

I feel at home at Blanc Labs. Here, I am encouraged to learn, grow, and pursue new levels of excellence every day. Leadership has been instrumental as they have nurtured me to rise to new heights and for that, I am grateful. When I think about the success in my career, I go back to the three values that I admired in my father: dedication, responsibility, and focus. I realize that life has come full circle and I carry on the legacy of his work in everything I do and every frontier I choose to explore.

To learn more about the values with which we are growing our team, please explore our mission and vision.

Have you ever wondered how search engines and email accounts are able to provide suggestions to complete a sentence while you’re typing it? Have you ever been curious about how your Gmail account knows how to classify your emails under the Primary, Social and Promotion tabs? How does Siri, Alexa, Echo or Cortana know to play a song when you ask it? The answer is deep learning, and as part of a series on the subject, we’re about to give you a sneak peek at the first part of this story: Classification.

The world is building a solid foundation of machine learning (ML) into various sectors, functions, and tasks in our everyday lives. There is a myriad of components that one may delve into when exploring ML but an area that we engage in extensively and is getting increasingly interesting, is deep learning applied to document and data capture or Intelligent Document Processing (IDP).

The ABCs of IDP

Let’s start with the basics: According to Bernard Marr at Forbes, “Deep learning is a subset of machine learning where artificial neural networks, algorithms inspired by the human brain, learn from large amounts of data.” IDP involves the capturing, extracting and processing of data from a variety of document types.

Now what’s so “exciting” about document and data capture? There are two types of documents from which you’d capture data: Structured and Unstructured documents.

• Structured: These are standard forms (ex: government forms) that have specific and unaltered fields and patterns of information.
• Unstructured: These are documents that don’t have any universal pattern. For this article, letters of employment would be good examples. Companies draft them in different formats and with different lengths (and cadence).

And with that established, lets delve into the two stages of how data is captured:

• Classification: Examining and defining a document
• Extraction: Capturing and recording key data from a document that has already been classified

There are two ways in which documents may be categorized: image processing and Natural Language Processing (NLP).

The Art of Image Processing

Here is an instance where machine learning models are trained to look at a document and understand the pattern of what it sees. It isn’t ‘reading’ the document but uses Convolutional Neural Networks (CNNs) to identify patterns within an image, which in turn informs its classification. We found this works well for more structured documents where patterns are identical while the content may be varied. However, where we came into a few issues was the ability to scale the process.

Why?

When you train a machine to resolve categorisation, through the image approach, you are identifying objects specifically. However, forms don’t possess visual features for image processing. Every time we had to retrain a new document type, it would need to be trained from scratch with new data. This took days and weeks. In addition, we started to work with unstructured documents and found that we needed a new solution to effectively categorize them faster.

Enter: Natural Language Processing

With NLP, Optical Character Recognition (OCR) and LTSM (long term short memory) networks are used to extract words, run analysis (determining the context of the words), and then classify the documents. Unlike image processing, NLP, along with transformer models considers the relationship between all the words in a sentence and determines the weight of each word to interpret its meaning. This reduces the training time for every new document introduced, making the entire process faster.

Where new document types may take a week to train the machine to classify using image processing, NLP does it in mere seconds.

Setting up for success

There are two things to consider when one starts a project with NLP to make the process easier:

• Determine goals: What information are you capturing and why. And what type of documents will be required to process?
• Organize data collection: Maintain the quality of data by building workflows or processes that support consistent quality of information and documents collected.

The Journey Ahead

When you look at algorithms, sentiment analysis and the capacity of machine learning to evolve its capabilities, the term ‘speed reading’ really is taken to a whole new level. Our story doesn’t end here. It is just the beginning; It’s an evolving journey of discoveries and we look forward to exploring other dimensions of our realizations, including our next chapter exploring extraction, with you very soon!

Explore Kapti, our intelligent document processing software to find out how the power of machine learning and automated document workflows can transform your organization’s loan processing experience.