Figure 2.
Video frame example
THE 3
rd
INTERNATIONAL SCIENTIFIC CONFERENCES OF STUDENTS AND YOUNG RESEARCHERS
dedicated to the 99
th
anniversary of the National Leader of Azerbaijan Heydar Aliyev
123
Conclusion
This research is aimed to detect any traffic accident in real time either
from surveillance cameras or register cameras by the utilization of
Convolutional Neural Networks (CNN). Project is in initial stage and has
ability to predict an accident with 34% accuracy.
References
1. https://pubmed.ncbi.nlm.nih.gov/31907688/
2. https://dl.acm.org/doi/abs/10.1007/s10916-019-1484-1
3. https://www.sciencedirect.com/science/article/pii/S2405959516300169
4. https://github.com/lopezbec/Traffic_Accident_Detection
USING ARTIFICIAL INTELLIGENCE IN AUTOMATION OF
FINANCIAL RISK MANAGEMENT
Mahira Asadzade
Baku Higher Oil School
Baku, Azerbaijan
mahire.asadzade.std@bhos.edu.az
Supervisor: Ph.D Associate Professor Leyla Muradkhanli
Keywords:
artificial intelligence, machine learning, risk management in finance, deep
learning, risk analysis, volatiliy forecasting, credit scoring, market risk, claims modelling.
Financial risk management avoids losses and maximizes profits, and
therefore is vital to most businesses. The ability of machine learning models
to analyze large amounts of both structured and unstructured data can
improve analytical capabilities in risk management and compliance, allowing
risk managers in financial institutions to identify risks in an effective and
timely manner, make more informed decisions, and make banking less risky.
Based on the source of risk factors, it is conventional to classify risk into four
high-level categories:
Market risk
,
Credit risk
,
Insurance and demographic
risk
, and finally,
Operating risk
[1].
Market risk is the risk arising from changes in financial indicators, such
as the exchange rate, interest rate, inflation, and so on. One of the key
measures related to market risk is
volatility
which reflects the uncertainty of
future asset prices in the financial market.
Gen- eralised Autoregressive
Conditional Heteroskedasticity (GARCH) model is an autoregressive moving
average model for conditional variance with p number of lagged squared
returns and q number of lagged conditional variance, so it is widely used by
practitioners for modelling time-variant volatility of financial time series [2].
Data-driven models, namely Support Vector Regression and Neural Networks
were applied to significantly improve forecast performance and the results
are shown below.
|