Category: Innovations

Welcome to our Innovations category, an expertly curated space wholly dedicated to spotlighting Signzy’s pioneering fintech solutions. As a leading entity at the vanguard of the fintech revolution, we are unceasingly pushing the limits, redefining the boundaries of the possible by employing breakthrough technologies coupled with ingenious problem-solving.

This specially designed category houses articles that offer an in-depth exploration of our latest product developments, unique features, and groundbreaking technologies. We are harnessing the power of the most advanced technologies at our disposal, from artificial intelligence and machine learning to blockchain and automation, building transformative solutions that are redefining the very contours of the fintech industry.

The innovations we bring to the table are meticulously designed to address the most critical challenges businesses face today. Our focus areas include enhancing customer experiences, bolstering security measures, and ensuring scrupulous regulatory compliance. By unraveling and simplifying intricate processes and introducing unprecedented efficiencies, we are empowering businesses to concentrate on their core competencies.

We invite you to navigate through our Innovations category to gain insights into how we are ingeniously leveraging technology and creativity to reshape the financial landscape. No matter who you are – a fintech enthusiast deeply interested in the sector’s developments, a potential client evaluating solutions, or a technology aficionado with a penchant for innovation – you will discover intriguing insights into our journey of innovation. Embark on this exciting voyage with us, and witness how innovative thinking is changing the world of finance.

How Digital KYC Can Prevent Ponzi Schemes In The US

Posted on | by Signzian

Introduction

In the early 1920s, Charles Ponzi created one of the first Ponzi Schemes depriving people of their hard-earned money. After a century, similar scams are on a decade high in 2020. Over 60 alleged Ponzi Schemes with a total of more than $3 billion investor funds were uncovered last year alone. Few reasons for this hike were unsatisfactory KYC check, the pandemic and its aftermath.

The COVID-19 outbreak was a tragic and fearsome event. Unfortunately, many fraudsters thought this a good time to make some unethical profit. The vulnerability of people and their desperate financial state has enabled them to fool the people and take their money. Most of this occurred due to the insufficient and improper KYC checks on such fraudsters by regulatory bodies and financial institutions.

Numerous people fell prey to claims of low-risk high returns schemes and programs. This will not stop unless the authorities make strict regulations for the verification of individuals and enterprises. The fist of justice, though stern is not swift enough. Thus the responsibility falls on the entire financial sector’s shoulders. It is up to banks and financial institutions to have advanced modes of KYC checks for proper verification and affirmation of security.

If nothing is done to ensure better verification of customers with advancing technology, this new decade will be bleak from here on. Let us have a look at how the coming years can fight such fraudsters and how we could have done it before too.

Why Do People Confuse Ponzi Schemes With Pyramids Schemes And MLMs?

 

In the US, Ponzi Schemes and Pyramid Schemes are illegal while most Multi-Level Marketing(MLM) Schemes are considered legal and people are tricked into investing in the former illegal opportunities. One of the reasons for this is people misunderstanding Ponzi Schemes and Pyramid Schemes for MLM. MLM is a metamorphosed step in direct selling. In MLM, existing distributors recruit new distributors for a capital fee. They primarily sell products directly to consumers without moderators. If the major source of revenue is from selling products and not distributorship, it is legal.

If the business model enables major profit from selling distributorship and minimal product sale revenue, then it is classified as a Pyramid Scheme. This is illegal because, as the recruiting multiplies, it becomes incredibly difficult for new recruitments. This causes sufficient returns for early investors but the later ones are sure to experience monetary loss.

Prima facie, Ponzi schemes resemble Pyramid schemes since both promise high returns with no or low risk. But the mechanics are where the similarities end.

Ponzi Schemes center around fraudulent management services for investments. People invest in funds for ‘portfolio managers’ promising multiplied returns. When the investors demand their money back, incoming funds from new investors are used to pay them off. The early investors mistakenly believe that they have increased profits, while the later investors are outright scammed. The individual who sets this system up controls the entire operation. They exclude any real investments while transferring funds from client to client.

Bernie Madoff’s Bernard L. Madoff Investment Securities LLC is considered the most successful fraud company to pull off a Ponzi Scheme. It still holds up with $65 billion deceived from over 5000 clients. With advancing technology, Ponzi schemes and frauds are expected to rise in the coming decade with at least one to surpass the Madoff ceiling.

 

The Necessity For Automated/ Digital KYC check

Digital/Automated KYC verification procedures leverage AI, ML, and other advanced technology to ensure clients meet regulatory standards with minimal dependency on internal resources.

This doesn’t imply that high-level decisions are automated, but the majority of legwork is automated primarily through Intelligent Process Automation(IPA). IPA combines collections of technologies that combine, manage, and automate digital processes. It is mainly constituted of Robotic Process Automation (RPA), Intelligent Document Processing (IDP), Artificial Intelligence (AI). Read more about Automation in Banking and Digital KYC.

These technologies are used for automated workflow, identification, verification times, extract data from documents, and to reduce screening. Collecting and analyzing data with IPA and ML provides financial institutions with a more sturdy and instantaneous picture of the client. This is the crucial element in preventing frauds like Ponzi Schemes. The constant surveillance for illegal activities always renders the fraudsters less volatile.

Some aspects of Digital KYC that prevent Ponzi Schemes and other financial fraud include:

  1. Strict identification and verification procedures ensure any malpractice or fraudulence in customers.
  2. More precise execution of processes reducing vulnerability to risk.
  3. Reduced Human errors as the majority of work is automated in a workflow.
  4. Reduced Time required renders responses swift denying time for fraudsters for their schemes.

Recent Ponzi Schemes That Could Have Been Prevented With Automated KYC check

 

1. Jeff and Paulette Carpoff- 2020

What Happened?- The SEC in January 2020 filed a case against Jeff and Paulette Carpoff, charging them for helming a $910 million Ponzi scheme. The money was obtained from 17 investors in California between 2011 and 2018. They used their solar generator companies to attract investors. But they did not manufacture even half of what was promised. The lease payments committed to early investors were obtained from later investors. The additional money was used for their lavish lifestyle. This included a sponsorship deal with Chip Ganassi Racing for a NASCAR Xfinity Series. Later the couple pled guilty.

How Could It Have Been Prevented?- The financial institutions involved did not conduct proper KYC check and other verification processes with this company in the beginning and when it added new investors. If they had, better transparency could have been maintained and the investors could have seen the scam from afar. The reason cited by the banks for the lack of this diligence was the impracticality of manually attending each investor and company for verification. A digital approach would have created a faster and reliable verification procedure. In essence, a scam like this could have been prevented to an extent with methods like Digital KYC.

2. Woodbridge Group of Companies- 2017

What Happened?- In the winter of 2017, The U.S. Securities and Exchange Commission (SEC) charged Woodbridge Group of Companies with a US$1.2 billion Ponzi scheme. It was helmed by Robert H. Shapiro. Woodbridge and 236 related LLCs filed for bankruptcy on December 4, 2017, in the Delaware Federal Court. This occurred amidst the absconding of relevant position holders and an ongoing investigation. More than 8400 investors fell prey to Shapiro’s scam. Due to the Bankruptcy declaration, these investors received zero returns as opposed to the 5 to 10 percent promised in the beginning.

How Could It Have Been Prevented?-The lack of sufficient financial checks on the individuals involved in the Woodbridge case is evident. Verifications on financial data could have prevented this. Even after the Government setting up federal portals, financial institutions are not using them to their maximum potential. With Digital KYC verification this could be changed and a more diligent form of verification could be introduced. It is high time banks and organizations accept this.

 

3. Burton Greenberg and Bruce Kane- 2015

What Happened?- A relatively smaller scam by Burton Greenberg and Bruce Kane in the state of Florida is worthy of notice. The fraudulent scheme ran for nearly a decade but came to a halt after the FBI arrested them on October 7, 2015. The scam operated with the name “Global Financial Fund 8, LLP”. They obtained millions of dollars from investors. It was used for personal expenses while they were assured safety of investment. Much of the money was found in institutions overseas including Turkey, Switzerland, and Italy. The two were sentenced to prison in 2016 after more than 9 years of scamming people.

How Could It Have Been Prevented?-Such individual and nuclear cases of Ponzi schemes mostly go unnoticed due to their lesser magnitude. But in time multiple of these add up to a great extent and can cause major crises- let us all not forget 2008. With diligent inspection on entry, such fraudsters, especially ones with previous records could easily be identified. Soon enough in the next decade, these fraudsters are going to use advanced technology to trick institutions and individuals. It is only sensible to upgrade the existing systems KYC check to meet such demands.

Conclusion

Ponzi Schemes are no new ideas. Fraudsters infuse technology to this brilliantly vice idea and seem to have no intent to stop it anytime soon. But we can’t let the public be the victims. Necessary measures need to be taken for safety. As always, nipping the problem in the bud is the most advisable solution. This requires authenticating the customers and the organizations. For this, using technology is not just a brilliant strategy, but an unavoidable one.

The financial sector has always adapted to technology swiftly. Even government bodies in this sector are keen on upgrading their security and processing. Since Ponzi Schemes and other financial frauds are projected to increase, necessary steps need to be taken. Digital KYC is one step towards this.

It is time the individual institutions in the sector acknowledge this and adapt. This will keep them stay ahead of the curve. The reluctance expressed by banks and financial organizations are understandable but rebounding. An early adaptation to technology like Digital KYC will only benefit them.

About Signzy

Signzy is a market-leading platform redefining the speed, accuracy, and experience of how financial institutions are onboarding customers and businesses – using the digital medium. The company’s award-winning no-code GO platform delivers seamless, end-to-end, and multi-channel onboarding journeys while offering customizable workflows. In addition, it gives these players access to an aggregated marketplace of 240+ bespoke APIs that can be easily added to any workflow with simple widgets.

Signzy is enabling ten million+ end customer and business onboarding every month at a success rate of 99% while reducing the speed to market from 6 months to 3-4 weeks. It works with over 240+ FIs globally, including the 4 largest banks in India, a Top 3 acquiring Bank in the US, and has a robust global partnership with Mastercard and Microsoft. The company’s product team is based out of Bengaluru and has a strong presence in Mumbai, New York, and Dubai.

Visit www.signzy.com for more information about us.

You can reach out to our team at reachout@signzy.com

Written By:

Signzy

Written by an insightful Signzian intent on learning and sharing knowledge.

What Is Automation In Banking And How Has USA Used It To Grow Its Economy?

Posted on | by Signzian

Introduction

The banking industry has always tried to stay ahead of the curve in being adaptive to modernization. It was one of the early adopters in the age of information and understood how much technology would incurve into people’s lives. This has enabled its growth as a pioneer and led it to become one of the largest consumers of Information Technology. Automation and AI are the next logical steps.

Automation in banking is the system of utilizing technology to operate banking processes through highly automatic means rendering human intervention to a minimum.

Gartner reported that the estimated expense on IT applications in the banking sector was $487 Billion in 2018. Lion’s share of this expense was for outsourced external companies which primarily constituted Business Process Outsourcing(BPO) companies. This added up to an approximate of $63 Billion being paid to these BPOs. Such precedent expenses can be avoided by evolving with the technology and the easiest way to minimize it is automation.

How has Automation Evolved Through the Ages?

 

Traditional Automation

Traditional Automation permits and processes machinery to perform tasks. It uses primarily APIs and other methods to integrate systems and developers must be well versed in the functionality of the target system. This may include steps in operational processes and methods.

Traditional automation is limited in some aspects as in application customization due to insufficient software source code. It is also affected by the limitations of APIs. Most of its methods are rather primitive for today’s digital transformation. Nonetheless, it is still prevalent in many places.

RPA

Robotic Process Automation(RPA) focuses on front-end activities and doesn’t need any shifts for backend operations as RPA works across different applications. RPA bots function at UI(User Interface) level and within the system like humans and provide better personalization and easy customization than traditional automation for users.

Some major features of RPA include:

  1. Reliance on easy to program functionality with reduced TAT
  2. Bots execute individual functions- email responses,data extraction,etc.
  3. Works from UI comprehending user actions.

It’s used for data collation, analysis, invoicing, email management, and other customer service functions. Implementing RPA will cut costs for banks on many levels of these spheres as RPA & traditional automation relieve Individuals from tedious tasks.

 

RPA- Market Revenues Worldwide (2016–2022)-Statista– Source

We must understand that RPA doesn’t replace any existing technology but works in tandem with the prevalent framework. In a nutshell, RPA handles repetitive, rule-based, and monotonous tasks and actions.

A common example of an RPA bot is the ubiquitous Chatbot. As RPA doesn’t have any AI involved, its scope to improve is limited. It doesn’t learn but helps the user. Here we discuss primarily RPA applications and Implementations.

Artificial intelligence

Artificial Intelligence is the latest technology for automation and mimics basic human intelligence, further advancing it. Such AI-enabled systems comprehend, evaluate, and respond to complex problems and situations efficiently by using Machine Learning algorithms. Some good examples of AI applications are NLP (Natural language processing) powered voice assistants such as Alexa, Google Assistant, and Siri.

Approximately 32% of service providers in the industry use AI technology to better customer experience and ease processing. They use technology like voice recognition, analytics, etc. This was reported in a joint research by Narrative Science and National Business Research Institute.

AI has expanded to such an extent that all the previous technologies used now fall under its own umbrella. Even then AI is met with some skepticism as it will completely take over the processing procedures and traditionalists may raise questions on dependability.

What Benefits Does Automation Offer that Makes Banking Better?

Automation provides the process of banking with versatile features that makes the entire procedure easier for banks and customers. Not only does it bring the safety and privacy of the customers to a higher standard, but also does it provide them with a fulfilling experience. Some of the features include:

  1. Better Customer Service- Data management becomes easier with RPA implementation. These include Daily inquiries, information transfer, application status, balance information, and others. This will free employee time for more critical decisions and tasks. An example is the functionality of a Chatbot which saves every involved party’s time.
  2. Improved Compliance- Banks are regulated by legislatures and other government bodies that prescribe many strict compliance guidelines. Accenture conducted a survey in 2016 in which 73% of respondents expected RPA to be a key enabler in compliance. This was because it increased productivity by being available 24 hours a day with immense accuracy.
  3. Accounts Payable- It requires vendor information extraction, validation, and payment processing. OCR(Optical Character Recognition) technology is used to obtain data from any physical form and transfers it for RPA where the rest of the processing occurs, thus making the process far more efficient than manual methods.
  4. Faster Credit Card Processing- Banks process credit cards within hours using RPA which used to take days with traditional methods. Proper data of transactions can be maintained and better evaluations of credit scores can also be done.
  5. Faster Mortgage Loan- Even a minor error can impede loan processing. RPA can accelerate the process by avoiding unnecessary errors and implementing proper checks which would reduce the processing time to minutes from days.
  6. Vigilant Fraud Detection- RPA tracks all transactions that may give out a red alert and recognises any fraud transaction pattern in real-time. This brings a considerable reduction in response time and can block and prevent fraud to a great extent.
  7. More Credible KYC Process- Know Your Customer (KYC) is mandatory for banks for each customer. KYC process compliance alone costs banks more than $384 million per year(Thomson Reuters). RPA can reduce this along with the time the customer would have to wait for a response.
  8. Data Report Automation- RPA helps generate reports without any error for stakeholders providing data in many formats. They can create a report by auto-filling the available report format with minimal errors and time.
  9. Easier Account Closure Process- Customers benefit Faster account closing process. This increases their affinity to the bank.

How is Automation Boosting The US Banking Sector?

Valued at USD 167.1 million in 2018 and anticipated to register a CAGR of 31.3% from 2019 to 2025, the global robotic process automation in the BFSI market size was rather unprecedented.

The advent of advanced technologies and a need for increased productivity of operations in the United States of America lead to the entire BFSI sector in the country to significantly boost its demand for RPA. Since the USA has a rich inventory of legacy systems, the incorporation and advancements of RPA were upstanding. This increased the agility and precision of processing.

Even casual users can check their accounts and set up automatic payments of their bills. Even KYC verification and other numerous functions are also possible in a much easier fashion. Numerous other back-end and front-end processes are automated using RPA.

 

Source: www.grandviewresearch.com

In the US a considerable level of RPA has been integrated as alternatives for services such as BPO, robot deployments at the enterprise level, etc which otherwise would have been tremendously expensive. Further, the initiative eliminated repetitive and time expending tasks which have been automated. It reduces the cost of such tasks from 25% to 50% and the TAT to a minimal amount.

Artificial Intelligence and RPA funding spent in the banking and finance industry in the United States increased at 82.9% during 2018 to reach US$ 696.3 million. Over the forecast period (2019–2025), spend on AI is expected to reach a CAGR of 28.4%, increasing from US$ 1,094.9 million in 2019 to reach US$ 6,289.1 million by 2025.

USA and Canada dominated the market for RPA in 2018 in the Banking industry. On average, a U.S. bank with USD 10+ billion assets spends approximately USD 50 million per year on CDD, KYC compliance, and onboarding. The increased expense of KYC and AML compliance coupled with the steep fines over regulatory scrutiny are necessitating financial institutions to adopt new technology and automation. This prevents identity theft, financial fraud, terrorist funding, and money laundering.

The USA and Canada are set to dominate the financial market with RPAs for at least the next half of the decade. Banks are targeting to preserve patrons and reduce customer attrition and RPA helps them as the customer data is strategized and used to contact the customer as required. North America valued at $376.2 billion in 2019 is projected to reach $721.3 billion by 2027. The digital payment segment being the largest service segment in the industry is expected to head the market with the increase in banking products and sales through online portals is also a helpful factor. In 2019 the digital sales sector was valued at $609.4 billion.

Top Banks in US Taking Automation to The Next Level

  1. JPMorgan Chase
    The biggest bank in the US, JPMorgan Chase, always stood in the first place when it came to technology investments. A tremendous investment of $11.4 billion in AI technology by the bank proves its enthusiasm for innovation and far-sighted outlook(Source-JPMorgan Chase Annual report 2019). The Bank uses it for improving their databases, search optimization, and Contract Intelligence (COiN)- a Machine Learning technology that uses chatbot systems to build vast databases of legal documents in a short time.
  2. Bank of America
    They primarily focus on fraud detection, trading functions, and chatbots. The Bank’s AI-enabled chatbot named Erica(Introduced in late 2017) understands texts and speeches. It not only acts as an inquiry bot but advises the user on suitable financial decisions he could take. Erica approximates 6 million users/customers as of March 2019. The $35 billion lender has invested in the past ten years more than $1 billion in mobile banking which is the simplest area of automation for customers. Their own study revealed that mobile customers have increased to 10% annually.
  3. CitiBank
    With an agenda to avoid money laundering and fraud actions, the bank is heavily investing in automation in general and AI technology in particular. They even partnered with Feedzai(2016) for detecting fraudulent transactions. They recognize patterns of multiple transactions from multiple locations where the customer usually doesn’t travel to. The bank has a global network of tech giants that take part in its 6 Citi Global Innovation Labs. With multiple advances in automation and technology, $600 million is expected to be saved per year by the bank.
  4. Wells Fargo
    Their chatbot system primarily focuses on clarifying the queries of customers without consuming too much time or requiring physical presence. They also developed a mobile app through predictive analytics. It alerts the customers on issues like exceeded bill payments, etc. It even guides the user with their travel plan and to buy flight tickets. In the year 2019 alone Wells Fargo had nearly spent $9 billion on technology and automation.

Conclusion

The global adoption of a digital era is inevitable making Banking and Automation essentially complementary to each other. The automation of the banking industry with the use of Traditional Automation, RPA, and AI have led developed nations like the USA to develop a more efficient and sustainable economy.

The reason why banks and financial institutions swiftly adopted IT is that their operations, when executed manually, consume immense time and effort from their employees as well as making them perform routine duties and actions, and in the process, missing the opportunity to move up the value pyramid. Automation produces a standardized audit trail, ensuring the right people have access to the proper systems and making sure that financial institutions stick to industry standards while decreasing expenses involved.

The necessity of Automation in Banking is precedented. Its implementation has been mostly successful, but as all things do, it too requires betterment. At the end of the day, the adoption of Automation for banks and other financial industries is a matter of ‘When’ rather than If’.

About Signzy

Signzy is a market-leading platform redefining the speed, accuracy, and experience of how financial institutions are onboarding customers and businesses – using the digital medium. The company’s award-winning no-code GO platform delivers seamless, end-to-end, and multi-channel onboarding journeys while offering customizable workflows. In addition, it gives these players access to an aggregated marketplace of 240+ bespoke APIs that can be easily added to any workflow with simple widgets.

Signzy is enabling ten million+ end customer and business onboarding every month at a success rate of 99% while reducing the speed to market from 6 months to 3-4 weeks. It works with over 240+ FIs globally, including the 4 largest banks in India, a Top 3 acquiring Bank in the US, and has a robust global partnership with Mastercard and Microsoft. The company’s product team is based out of Bengaluru and has a strong presence in Mumbai, New York, and Dubai.

Visit www.signzy.com for more information about us.

You can reach out to our team at reachout@signzy.com

Written By:

Signzy

Written by an insightful Signzian intent on learning and sharing knowledge.

Explore Signzy's latest insights on advancements in image forgery technology. Learn how innovation is reshaping authentication and security measures

Image Forgery: Innovations In Technology By Signzy

Posted on | by Signzian

Image forgery has long been a pressing issue in the realms of digital media, cybersecurity, and even legal proceedings. As technology advances, so do the techniques for creating increasingly convincing forgeries. This raises critical concerns for the integrity of digital information and calls for innovative solutions to detect and prevent fraudulent manipulations.

While Facebook, Microsoft, and many others are banding together to help make machine learning capable of detecting deepfakes in videos, we at Signzy are trying to solve a similar problem, detecting fakes in documents. In the journey of building the global digital trust system, we at Signzy had to solve this major challenge of detecting image manipulations in identity documents.

 

Fig 1.0 Example of our forgery detection in action

In this blog, I will try to explain our approach in building an innovative image manipulation detection approach using deep learning.

 

 

The above images are examples of the advancements in image manipulation techniques. It takes a considerable effort for a human to find out that the image is forged. The features which distinguish real and fake are less, which makes it difficult to detect with human eyes.

Our objective was to build a system which could detect image manipulated documents.

Our first step was to create a dataset of forged documents to test the algorithm. With our expertise and domain knowledge in this field we came up with various scenarios on how an intruder would forge a document. The corresponding data for these scenarios was prepared by photoshop experts.

The forged documents were of mostly two categories.

  1. Copy paste : A region of the image copied from a particular document and pasted into a different document.
  2. Copy move : A region of the image copied from a particular document and pasted into the same document.

Copy paste

This is the type of forgery when a fraudster tries to copy a face from one document into another document. Our goal was to detect these forged regions and to classify the document as fake or real.

 

The dataset that we created manually using photoshop experts was not enough to train any deep learning solution around it. So we developed image processing algorithms which could generate synthetic forged data. Now all set for the experimentation.

For forged region detection, our approach was to first start off with the state of the object detection methods. We tried with FRCNN to predict the bounding boxes of the forged region along with the class information. FRCNN uses convolution nets to extract feature maps from the input image. These maps are then passed on to a Region Proposal Network which will give proposals for bounding boxes. These proposals are passed on to the ROI pooling layer which converts all the proposals to the same size. Finally, they are passed on to a fully connected layer to predict bounding boxes and classes. This method did not give us better results because the forged regions were of very small size.

Our second approach was to train a patch-based classifier which could classify between real and forged patches. The idea was on the assumption that if the copied image region has a different compression footprint when compared to the region to which its copied to, there would be a strong shift in the way that the pixels are grouped. This method proved to be very efficient.

 

It almost gave us around 97% accuracy. We did a lot of ablation studies to find the right configurations which I can’t reveal due to IP issues.

Copy Move

This is the type of forgery when a fraudster tries to change any text in an image by copying a similar text from the same image. For example, changing dates. Our goal was to detect these forged regions and to classify the document as fake or real.

 

There is a lot of literature related to detection of this type of forgery. The popular one is DCT based feature matching. In this method, DCT followed by quantization is performed on a 16×16 patch extracted from the image. The similar operation is performed throughout the entire image and all the matrices are sorted. Then for each row in the matrix the corresponding shift vector is calculated. If two regions are copied the shift vector of those regions would match. A very powerful algorithm that works well in most scenarios. But in our use case, since a document has many regions that have the same DCT values this method couldn’t be applied.

Our method involved two parallel networks. First, an encoder-decoder network predicts pixel-wise forged regions. A second network runs in parallel that finds feature maps which are in correlation with forged region predicted by the first network. Both networks are trained together with a cumulative loss function. I regret as I can’t reveal the full solution due to IP issues.

To summarize this blog, I had explained the two major types of forgeries which can be done in documents. Also, I had tried to explain the approaches we took to solve this challenging problem. Hope you had a nice read.

About Signzy

Signzy is a market-leading platform redefining the speed, accuracy, and experience of how financial institutions are onboarding customers and businesses – using the digital medium. The company’s award-winning no-code GO platform delivers seamless, end-to-end, and multi-channel onboarding journeys while offering customizable workflows. In addition, it gives these players access to an aggregated marketplace of 240+ bespoke APIs that can be easily added to any workflow with simple widgets.

Signzy is enabling ten million+ end customer and business onboarding every month at a success rate of 99% while reducing the speed to market from 6 months to 3-4 weeks. It works with over 240+ FIs globally, including the 4 largest banks in India, a Top 3 acquiring Bank in the US, and has a robust global partnership with Mastercard and Microsoft. The company’s product team is based out of Bengaluru and has a strong presence in Mumbai, New York, and Dubai.

Visit www.signzy.com for more information about us.

You can reach out to our team at reachout@signzy.com

Written By:

 A B Sarvanan

Tech Lead — AI Team (Signzy)

 

A more reliable, secure and private video conferencing

Posted on | by Signzian

Till the COVID-19 pandemic tapers down, work from home and remote functioning have become our current “normal”. We’re in a time where digital transformation has been forced upon companies to remain afloat and surf the wave of changes this situation calls for.

Work processes are adopting new workflows and technology to ensure this period is productive and not stagnant. Staying connected is at the top of the list of work from home priorities. All interaction and meetings have now taken to calls and video conferencing. Third party video conferencing tools were aggressively downloaded by millions in this span. A few weeks in, however, privacy concerns have started circling many video conferencing platforms.

Privacy plague

Video conferencing has surged in popularity recently. Everything is being done online. From taking school lessons, virtually attending weddings, and hosting cabinet meetings. But, it’s privacy shortcomings have now been brought to the fore. In an era of social distancing, as everything takes to the digital, online security cannot be distanced from. It is imperative to protect personal data and organization data shared over the digital space. With most of the tech industry holed up at home, the sheer volume and frequency of shared data has multiplied.

In the past few weeks an online harassment method termed “Zoombombing” emerged [1]. Malefactors disrupted calls on the platform Zoom by flashing inappropriate content such as pornography, hate speech, and shock videos. Privacy advocates also revealed that popular video conferencing tools were caught sending personal data to Facebook. News reports are replete with such privacy concerns exposing these apps’ vulnerabilities.

Whether you’re the type to have tape over your laptop camera or not, it is safer to distance yourself from unsafe platforms. At the same time, privacy does not have to be sacrificed at the feet of convenience.

Digital Trust for Banks and Financial Institutions

For banks and financial institutions, it is imperative to maintain processes that do not jeopardize the privacy of their customers. And at the same time offer protection from fraud. A successful example of a banking workflow that is adapted to be 100% digital is the Know-Your-Customer process for onboarding and customer verification.

Using VideoKYC ensures there are no compromises on safety standards. We have honed the process with numerous layers of checks and balances. These include AI-enabled video forensics and identity document checks. They eliminate security gaps by combining human scrutiny with both software and ML and AI-enabled learning.

While generic video conference tools are not secure enough for financial services, our systems have always been designed for banking grade technology. We’ve developed our tools in a way that banks and financial institutions trust us with their data. This has now been taken a step further with our video-conferencing tool. It is developed keeping the needs of banks and financial institutions in mind.

In some cases the COVID-19 crisis is serving as an impetus to go digital. In other cases digital help is needed to coordinate between offsite and onsite officials. It is a daily need for confidential cross-country interaction. Either way video conferencing is essential to preserve uninterrupted work.

Enumerated below are some uses and features of this technology:

  • Since it is a safe and secure method of communication with no scope of privacy infringement, banks can schedule a call with the customer. This will cut down on the back and forth time that accompanies financial transactions.
  • Instead of the relationship managers from banks having to be physically present, they can now use our tool to communicate with the users. With COVID-19, this can help ensure banks continue their normal functioning, with higher efficiency. Our compliant VideoKYC has now merged with video conferencing, allowing REs to clarify issues in real time.
  • The features are customizable for the bank. The organizer (bank) can restrict the functionalities available to the user. For example, a bank can decide they do not want to let the user switch off video during the interaction.
  • The technology is good for auditing the call. Any breach in protocol can be caught through this auditing. Since this has been developed keeping banks in mind, no other third party software enables this.

Certainty of security in a time of uncertainty

We can’t say till when you’ll have to work from home. But, we can ensure that our tools are tested to be secure, simple, and even compliant.

  • No leakage of data
    The platform prevents the leakage of personal data such as email IDs and photos.
  • End-to-end encryption
    We ensure end-to-end encryption of all data shared over our platform. A third party cannot decrypt the calls.
  • Seamless communication
    While the technology ensures full protection of the interaction, the UI ensures it is also easy to use and seamless.
  • Only a person with an invitation can join the call. This prevents any hackers or miscreants from disrupting the call. Our video conferencing tool ensures there is no scope for malicious activity such as “Zoombombing” to occur.
  • Signzy has control over the data flow. There have been recent concerns where data is being routed through China by video conferencing platforms [2].

Companies that adopt Signzy’s secure video conferencing have one less thing to worry about in these strange times.

About Signzy

Signzy is a market-leading platform redefining the speed, accuracy, and experience of how financial institutions are onboarding customers and businesses – using the digital medium. The company’s award-winning no-code GO platform delivers seamless, end-to-end, and multi-channel onboarding journeys while offering customizable workflows. In addition, it gives these players access to an aggregated marketplace of 240+ bespoke APIs that can be easily added to any workflow with simple widgets.

Signzy is enabling ten million+ end customer and business onboarding every month at a success rate of 99% while reducing the speed to market from 6 months to 3-4 weeks. It works with over 240+ FIs globally, including the 4 largest banks in India, a Top 3 acquiring Bank in the US, and has a robust global partnership with Mastercard and Microsoft. The company’s product team is based out of Bengaluru and has a strong presence in Mumbai, New York, and Dubai.

Visit www.signzy.com for more information about us.

You can reach out to our team at reachout@signzy.com

Written By:

Signzy

Written by an insightful Signzian intent on learning and sharing knowledge.

 

Removing blur from images

Posted on | by Signzian

Everyone misses perfect shots once in a while. Yeah, that’s a pretty shame (We all do that all the time!!!).

There are special moments which we want to capture to make them memorable for lifetime, but just because your camera shook or amount of noise in your camera can really hamper those special moment resulting in blurred images (Maybe your subject is on the move, the reason is not always bad cameras but bad timing as well!!!).

So, if you are also one of us who misses out their special moment, this post is just for you. In this post, you will get to know how you can restore blurred images. All the thanks and applause goes to Neural networks.

What are you going to learn?

From this blog post, you will learn how to make use of the neural network by image deblurring technique with the help of Scale-recurrent Networks. For more info on the technique, you can access this link. The network takes sequence of blurry images as input at different scales and produces a finite set of sharp images. The final output image is at the full resolution.

Figure 1: SRN architecture from the original paper

The method above uses end-to-end trainable networks for the images. Then it used multi-scale convolutional neural network with the approach of state-of-art.

These methods embark from an abrasive measure of the blurry images, and gradually try to recover the suppressed image at higher resolutions.

This Simple Recurrent Network aka SRN makes use of scale recurrent network for multi-scale deblurring. The solver and the corresponding parameter at each scale in a well-established multi-scale method are always same. This is a natural choice as it simply aims to solve the very same problem. If we vary scales in different parameters, then it may cause instability and the extra issue of unrestrictive solution space. Another concern to address here is the input images may have different motion scales and resolutions.

If you allow too much parameter tweaking in each scale, then this might result in creating a solution that is overfitted to a specific motion scale. There are people who believe that this method is also applied to CNN-based methods. Still, there are some recent cascaded networks that still prefer to use independent parameters for every single scale. They justify this method with a pointer which seems quite plausible. They proposed that sharing networks weights across different scales can significantly deteriorate training difficulty and also introduce stability benefit.

Their experiment shows that how with the help of recurrent structure and the combination of the above advantages, the end-to-end deep image deblurring framework can greatly mend training efficiency. They only use less than 1/3rd of the trainable parameters with faster testing time. Apart from this, their method is proven to produce high-quality results both qualitatively and quantitatively. Let’s not dive deep in the research paper for now. Allow me to present you our use-case of this deblurring technology.

We are well-established Global Digital Trust Company, which functions primarily in the domain of verification processes. For this verification process, our customers have to click photos of their documents and submit it for verification. There are probable chances where these photographs may be blurred either due to camera shake or any motion which causes difficulty in reading the document text.

To solve the blurred image problem, we fed these images in the aforementioned Deblurring Model. The results were exhilarating. Below are some of the samples,

Concluding Remarks

What do you learn from this blog? You learn the use of scale recurrent network for deblurring images. With this technology, you can easily extract data from blurred identity card images. You don’t have to poke your customers again and again for the re-submission of the documents due to bad-quality or blurred images. Thanks for the read and do leave a comment to let me know what you feel about this technology. Adios for now fellas!!!

About Signzy

Signzy is a market-leading platform redefining the speed, accuracy, and experience of how financial institutions are onboarding customers and businesses – using the digital medium. The company’s award-winning no-code GO platform delivers seamless, end-to-end, and multi-channel onboarding journeys while offering customizable workflows. In addition, it gives these players access to an aggregated marketplace of 240+ bespoke APIs that can be easily added to any workflow with simple widgets.

Signzy is enabling ten million+ end customer and business onboarding every month at a success rate of 99% while reducing the speed to market from 6 months to 3-4 weeks. It works with over 240+ FIs globally, including the 4 largest banks in India, a Top 3 acquiring Bank in the US, and has a robust global partnership with Mastercard and Microsoft. The company’s product team is based out of Bengaluru and has a strong presence in Mumbai, New York, and Dubai.

Visit www.signzy.com for more information about us.

You can reach out to our team at reachout@signzy.com

Written By:

Signzy

Written by an insightful Signzian intent on learning and sharing knowledge.

 

1 … 4 5 6 7