USE OF ADVANCED

ANALYTICS IN QUANTITATIVE
FINANCE
FINANCIAL ENGINEERING AND RISK MANAGEMENT

APRIL 11, 2022

PRAKHAR GUPTA
PGDM GEN -019
WHAT IS ADVANCED ANALYTICS?

Advanced analytics is a data analysis methodology that uses predictive modelling, machine
learning algorithms, deep learning, business process automation and other statistical methods
to analyse business information from a variety of data sources.

Advanced analytics uses data science beyond traditional business intelligence (BI) methods to
predict patterns and estimate the likelihood of future events. This in turn can help an
organization be more responsive and significantly increase its accuracy in decision-making.

Often used by data scientists, advanced analytics tools both combine and extend prescriptive
analytics and predictive analytics while adding various options for enhanced visualization and
predictive models.

WHAT IS QUANTITATIVE FINANCE?

Quantitative finance is the use of mathematical models and extremely large datasets to analyse
financial markets and securities. Common examples include

 The pricing of derivative securities such as options, and

 Risk management, especially as it relates to portfolio management applications.

Professionals who work in this field are often referred to as “Quants.

As you know Advanced Analytics includes

 Machine learning

 Predictive Modelling

 Deep Learning and many business process automation. Let’s look at deep learning
broadly.

1|Page
WHAT IS DEEP LEARNING?

Deep learning is a machine learning technique that teaches computers to do what comes
naturally to humans: learn by example. Deep learning is a key technology behind driverless
cars, enabling them to recognize a stop sign, or to distinguish a pedestrian from a lamppost. It
is the key to voice control in consumer devices like phones, tablets, TVs, and hands-free
speakers. Deep learning is getting lots of attention lately and for good reason. It’s achieving
results that were not possible before.

In deep learning, a computer model learns to perform classification tasks directly from images,
text, or sound. Deep learning models can achieve state-of-the-art accuracy, sometimes
exceeding human-level performance. Models are trained by using a large set of labelled data
and neural network architectures that contain many layers.

HOW DOES DEEP LEARNING ATTAIN SUCH IMPRESSIVE RESULTS?

In a word, accuracy. Deep learning achieves recognition accuracy at higher levels than ever
before. This helps consumer electronics meet user expectations, and it is crucial for safety-
critical applications like driverless cars. Recent advances in deep learning have improved to
the point where deep learning outperforms humans in some tasks like classifying objects in
images.

While deep learning was first theorized in the 1980s, there are two main reasons it has only
recently become useful:

 Deep learning requires large amounts of labelled data. For example, driverless car
development requires millions of images and thousands of hours of video.
 Deep learning requires substantial computing power. High-performance GPUs have a
parallel architecture that is efficient for deep learning. When combined with clusters or
cloud computing, this enables development teams to reduce training time for a deep
learning network from weeks to hours or less.

2|Page
TECHNIQUES IN DEEP LEARNING

 Classic Neural Networks: Also known as Fully Connected Neural Networks, it is often
identified by its multilayer perceptron’s, where the neurons are connected to the
continuous layer. It was designed by Fran Rosenblatt, an American psychologist,
in 1958. It involves the adaptation of the model into fundamental binary data inputs.
There are three functions included in this model: they are: Linear function & Non-
Linear function.
 Convolutional Neural Networks: CNN is an advanced and high-potential type of the
classic artificial neural network model. It is built for tackling higher complexity, pre-
processing, and data compilation. It takes reference from the order of arrangement of
neurons present in the visual cortex of an animal brain. The CNNs can be considered
as one of the most efficiently flexible models for specializing in image as well as non-
image data.
 Recurrent Neural Networks (RNNs): The RNNs were first designed to help predict
sequences, for example, the Long Short-Term Memory (LSTM) algorithm is known for
its multiple functionalities. Such networks work entirely on data sequences of the
variable input length. The RNN puts the knowledge gained from its previous state as
an input value for the current prediction.
 Generative Adversarial Networks: It is a combination of two deep learning techniques of
neural networks – a Generator and a Discriminator. While the Generator Network yields
artificial data, the Discriminator helps in discerning between a real and a false
data. Both of the networks are competitive, as the Generator keeps producing artificial
data identical to real data – and the Discriminator continuously detecting real and unreal
data.
 Backpropagation: In deep learning, the back propagation or back-prop technique is
referred to as the central mechanism for neural networks to learn about any errors in
data prediction. Propagation, on the other hand, refers to the transmission of data in a
given direction via a dedicated channel. The entire system can work according to the
signal propagation in the forward direction in the moment of decision, and sends back
any data regarding shortcomings in the network, in reverse.

3|Page
USAGE IN FINANCE

 Algorithmic Trading: Algorithmic Trading is the process of creating a computational

model to implement buy-sell decisions in the financial market. Other than being based
on mathematical models, a trader can use deep learning techniques that use
approximation models to implement buy and sell trades.

 Price Forecasting: Traders and experts in the financial industry have relied heavily on
computers over the decades, but have been able to take it to the next level with high
performance computing (HPC) running GPUs. These systems also allow people to
execute complex, memory heavy algorithms that require millions or even billions of data
points on their local machine to execute financial trading strategies, as well as price
forecasting using deep learning techniques such as Recurrent Neural Network (RNN)-
Short time horizon RNN is used for data with a sequential order, such as a time series
database. Long Short Term Memory Models (LSTM) — longer time horizon
compared to RNN LSTM is a variation of RNN with added parameters in order to
support longer memory so that the forecasted time horizon can be longer.

 Fraud Detection: The world of finance is riddled with fraud and deception. Hackers
and scammers are forever trying to steal confidential personal information and internal
company information to sell. Firms are under major scrutiny by governments worldwide
to upgrade their cybersecurity and fraud detection systems. Machine learning and deep
learning is now used to automate the process of searching data streams for anomalies
that could be a security threat. Algorithm like autoencoder of deep learning is used for
fraud detection.

 Customer Service: Financial services companies use finance-specific chat bots with
deep learning models to improve user experience. Deep learning based solutions bring
personalized services to customers. According to customer’s financial activities, virtual
assistants can Deep learning algorithms can identify potential churn by analysing
interactions. This capability helps insurance companies and banks to offer discounts
and new plans and protect their customer base.

4|Page