Data Mining and Engineering in Finance

This marcus evans conference will drive initiatives to build an ecosystem of quality data for trade and risk, through embedding data quality efforts within the use of a central data repository, the application of synthetic and legacy data, the role and limitations of machine learning, and use of appropriate data visualisation techniques.

As the volumes of data held by financial institutions increase, so too does the importance of data analytics. The role of data mining within financial institutions has seen a dramatic increase in recent years which shows signs of steadily continuing. Establishing the best practices to facilitate mining and engineering efforts to make your data work for you will be pivotal in ensuring that your institution is the most profitable it can be. With the improvement of data culture and the prevalence of centralised data comes the issues of dirty or noisy data, heterogeneity and the possibility for anomalies, alongside this we are seeing a marked increase in the use of legacy data and external data vendors. These offer some of the biggest challenges for data mining and engineering within financial institutions, but also present the best opportunities for improvement and optimisation. Meeting these challenges and understanding the best way to navigate them could present yet further opportunities to improve your use of data and so increase your overall profitability.