Article | February 25, 2020
Fintech is one of the fastest-growing industries, owing to the rising penetration of internet users. There is a paradigm shift to mobile devices for performing financial transactions and related actions. Behind the booming fintech market, there are several technologies that are contributing to making the system fast, secure, and scalable. One such technology is Artificial Intelligence (AI). The AI in the fintech market is estimated to reach USD 35.40 billion by 2025 ( Mordor Intelligence).
Article | May 26, 2021
The enormous amounts of data accessible to banks and their high demand for forecasting make the financial industry a perfect area for machine learning (ML) to shine. In this article, we explore the current applications of machine learning in banking when it comes to risk management, define its challenges and provide a future outlook.
Credit Risk Management
For the past few decades, banks have mostly used logistic and probit regression models for credit risk assessments and internal risk management. However, all conventional models inherit the same flaw — they predict outputs based only on linear relationships between input variables.
This limitation was exposed in the catastrophic 2008 housing market crash. Although the crisis’s negative consequences have been multiplied by uncontrolled sales of credit default swaps and other complex financial instruments, the fundamental reason for failure was in the inaccurate credit risk model.
In the aftermath, with the intent to force financial institutions to provide more detailed reports, The Federal Reserve’s CCAR now requires banks to account for more than 2,000 economic attributes. Consequentially, this also led to other regulating authorities introducing new standards that improve supervisory data quality and reporting.
At the same time, with the proliferation of banking apps, social media, and digital communication overall, financial institutions now collect lavish amounts of unstructured data. If gathered and processed correctly, these new datasets can help gauge critical insights for a wide range of banking operations.
This is where machine learning comes into play. More advanced non-linear approaches to credit risk modeling including neural networks enable banks to make predictions with a previously unseen level of accuracy and granularity.
The utter superiority of machine learning over traditional credit risk modeling approaches comes at the cost of the prevailing ‘black box’ problem. While we can decide to trust ML algorithms based on statistical evidence of their feasibility, current regulatory constraints won’t allow it to happen.
However, machine learning can still be used to a great extent while being regulation-compliant. Even simple linear machine learning approaches still yield more accurate results than conventional ones. Many banks also use unsupervised machine learning methods to explore data, while using traditional classification and regression models to make predictions.
Fraud Management and Surveillance
Nowadays, the majority of banks’ fraud detection systems use rule-based approaches. This causes banks to deal with a significant number of false positives, forcing them to spend inordinate amounts of resources to distinguish meaningless behavioral deviations from real threats.
The ability of machine learning to capture subtle trends and uncover non-linear relationships allows banks to get a complete picture of a client’s activity and significantly lower the probability of false positives. For example, by integrating ML into its fraud detection model, Danske Banks managed to reduce false positives by 60%.
Similar to many other AI-based solutions in the financial space, the biggest adoption hurdles concern regulations and the unexplainability of AI systems. For example, depending on the jurisdiction, banks are often unable to provide developers with sensitive information related to past breaches. Next, the outputs of unsupervised monitoring systems sometimes can’t be explained, which makes them non-compliant.
However, financial institutions have found a way to at least partly leverage the power of ML for fraud management. A fraud prevention system’s alerts will still be triggered by rule-based models, but the integration of an ML algorithm on top of them can allow adjusting surveillance methods to a person’s behavior fluctuations. Such ML models are typically less complex and explainable, which makes them applicable in a regulatory context.
Article | April 7, 2020
FinTech industry has 2008 crisis to thank for its tectonic rise. A number of ingredients (e.g. cheap funding, mistrust for banks, availability of ex banking talent, etc) came together that turned last recession into a platform for the launch of a wave of FinTech innovations. Since FinTech was almost born out of the last crisis, it is only natural to wonder how Corona Virus-induced crisis will reshape FinTech.
BITCOIN AND CRYPTO
Article | October 26, 2020
If the history have taught us anything it’s to never trust anyone else with your digital money. That is why when dealing with digital money such as cryptocurrency or tokens you should always store it at another place from where you bought it. Coinlager is doing exactly this, focusing on what its primarily feature is – to allow customers to buy cryptocurrencies in a quick, transparent and safe manner.
Ever since Satoshi mined the first Bitcoin crypto has been on the rise. In the beginning it was more of a subculture rather than a respected currency, something which has definitely changed over the past decade.
There was one company for those of you who remembers called MT Gox that was the number 1 choice for any cryptocurrency trader between 2010 – 2013, at most the covered 70% of the Bitcoin tradable market.
In February 2014 it however came to an abrupt stop since MT Gox announced that approximately 850,000 Bitcoins had been stolen from their Hot Wallet, valued at $450 million at that time.
Even though the MT Gox hack is by far the biggest almost all of the larger exchanges have at some stage been targeted by hackers and in some cases succeeded in stealing cryptocurrencies.
“We were actually one of the early adapters to crypto back in 2011, using MT Gox as a day-trading solution to increase our assets of Bitcoin. Everything were going smoothly until the crash in 2014 where we also lost all our Bitcoins. We haven’t really spent too much time dwelling on it, but when we see that people are still relying too much on using the same company for both thee crypto and the wallet service we thought we had to do something about it. The problem has always been that seperatiing the two services have not been user-friendly – this is what we are changing, giving the customers a super easy and quick way to buy their crypto and send it over to their desired wallet.”
So what is it that Coinlager essentially does? It’s simple, we sell cryptocurrencies to the customers. Customers can register over at Coinlager in seconds and be able to purchase their favourite cryptocurrency immediately. Relying on modernised technologies we can verify the customers in real-time, giving them the chance to not have to wait for hours or even days when their account becomes activated.
It doesn’t have to be overly complicated where customers do not understand what they are buying or how much it costs. With Coinlager we show the customers A) What they are buying B) What our fees are C) Where the crypto will be sent to (customer’s choice).
If you are interested in buying crypto, come check us out here: https://coinlager.com/
If you have a question, feel free to email us at firstname.lastname@example.org