{"id":8082,"date":"2021-02-16T19:22:09","date_gmt":"2021-02-16T19:22:09","guid":{"rendered":"http:\/\/ismiletechnologies.com\/?p=8082"},"modified":"2022-06-27T20:41:57","modified_gmt":"2022-06-27T15:11:57","slug":"use-cases-of-ml-in-azure-databricks-for-the-finance-sector","status":"publish","type":"post","link":"https:\/\/ismiletechnologies.com\/en_us\/machine-learning\/use-cases-of-ml-in-azure-databricks-for-the-finance-sector\/","title":{"rendered":"Use cases of ML in Azure Databricks for the finance sector!"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\"ImageMachine learning in finance sector: <\/strong>\u00a0Machine Learning has penetrated almost every industry and is being\u00a0extensively used for carrying analytical work\u00a0which\u00a0helps the company make important business decisions.\u00a0Talking about the finance sector, it is a huge industry\u00a0consisting of\u00a0insurance, banking,\u00a0real estate, etc.\u00a0\u00a0<\/figure>\n
There is always data\u00a0involved with any business and if that data is harvested and put to proper use using Data\u00a0Analytics\u00a0and Machine Learning\u00a0techniques, we can generate great insights\u00a0that otherwise are\u00a0not possible by\u00a0any means of manual data inspection.\u00a0Now, before we understand what is Azure data bricks and why to use them for our purpose, let us first understand the use cases\u00a0of ML in the finance industry.\u00a0<\/figure>\n
Use Cases in\u00a0<\/strong>Banking Industry<\/strong> :\u00a0<\/figure>\n
Customer 360:<\/strong>\u00a0Analyzing customer data to understand customer preferences and\u00a0what type of banking service they might be interested in. This helps the industry\u00a0design offers and promotion strategy that attracts\u00a0customers\u00a0to avail\u00a0baking related services.\u00a0\u00a0<\/figure>\n
Banking risk management:<\/strong>\u00a0Risk analysis\u00a0for baking sector using past data transactions. Loan default analysis and prediction\u00a0are used by banks to determine whether a\u00a0person should be provided any kind of loan or not or of what amount should be provided. This can be determined by analyzing the past data and transaction history as well as\u00a0his\u00a0assets and\u00a0occupation-related data.\u00a0<\/figure>\n
Banking fraud detection:\u00a0<\/strong>Frauds are very common in\u00a0online\u00a0banking\u00a0transactions and since the majority of the retail market is moving to eCommerce, there is a spike in the number of online transactions in recent years. This has also given rise to online\u00a0frauds. Machine learning\u00a0models when trained with data of fraudulent transactions can identify whenever\u00a0such transaction occurs.\u00a0This use case is also heavily leveraged by eCommerce companies.\u00a0<\/figure>\n
Credit Scoring models: A credit:<\/strong> score is a\u00a0numerical\u00a0measurement\u00a0based on an analysis of\u00a0a person\u2019s credit files to determine his creditworthiness. This score is used to understand\u00a0the financial capability of a person. It is majorly used by banks and real estate companies to\u00a0determine the creditworthiness of a person before making any financial or asset offer to them.\u00a0Credit scoring systems undertake plenty of different factors\u00a0to measure the credit score of a person\u00a0just like a loan default\u00a0identification system.\u00a0<\/figure>\n
Use Cases in Insurance Industry:<\/strong>\u00a0<\/figure>\n
Insurance Claims Automation:\u00a0<\/strong>Claiming insurance is a very complex process as it undergoes rigorous inspection of the situation before a claim in\u00a0process. Using the customer-centric data, this process can be\u00a0automated,\u00a0and the ML model\u2019s outcomes can be used to decide\u00a0on claims.\u00a0More the data\u00a0is used to train such models, more accurate results can be obtained any many different aspects of the insurance\u00a0industry can be automated.\u00a0\u00a0<\/figure>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

<\/p>\n

Actuarial science (risk analysis in the <\/strong>insurance industry):<\/b>\u00a0Actuarial science is a methodology that uses mathematical and\u00a0statistical techniques to assess risk in\u00a0the insurance industry.\u00a0Machine learning can\u00a0be used here to train models which can then detect the changes in data and analyze potential future risk for the industry.\u00a0It is much faster and accurate than manual actuarial analysis.\u00a0<\/p>\n

<\/p>\n

Case Management:\u00a0<\/strong>Process automation\u00a0of data, document classification and clustering,\u00a0analytics,\u00a0and visualization, all can be done by building a pipeline of ML models. All these aspects of case management can be\u00a0automated,\u00a0and a model\u00a0can process these tasks automatically as soon as case-related data is available.\u00a0\u00a0<\/p>\n

<\/p>\n

Personalized offers<\/strong>:\u00a0<\/strong>Recommendation systems are very well known these days in\u00a0almost every industry. They track the user activity from the browser or mobile app and that data is then used to show\u00a0related\u00a0lucrative\u00a0offers\u00a0and promotions to the\u00a0user.\u00a0Another term for it is targeted ads and marketing.\u00a0\u00a0<\/p>\n

<\/p>\n

Use Cases in Stock Market<\/strong>\u00a0<\/p>\n

<\/p>\n

Alternative data<\/strong>:\u00a0Data\u00a0is used by investors to analyze the performance of a company which can then be\u00a0used for investment-related decisions. Purchasing stocks\u00a0or investing\u00a0in a company needs an analysis of the company\u2019s performance. This can help make decisions related to what types and how big the investment can be made to ensure it turns into profit in the future.\u00a0<\/p>\n

<\/p>\n

Back\u2013testing<\/strong>:\u00a0It is a very\u00a0renowned method that involves the use of\u00a0predictive models\u00a0on\u00a0historical\u00a0stock market\u00a0data for stock\u00a0price\u00a0prediction. Many people invest in the stock market\u00a0in large or small amounts.\u00a0Prices of stock are changing every second\u00a0which generates a huge amount of data.\u00a0This data is leveraged using big data technologies and machine learning\u00a0to predict future prices of stock. This helps in buying and selling the stock.\u00a0Azure Databricks is one such platform\u00a0that enables building ML models over a large scale of data using parallel processing engines such as Spark.\u00a0\u00a0<\/p>\n

<\/p>\n

Trading cost analysis:<\/strong>\u00a0Data of trading orders\u00a0can be analyzed to\u00a0predict cost and\u00a0other parameters\u00a0and performance analysis.\u00a0This type of analysis by a company can provide meaningful insights to its clients and help recommend trading options to them. These types of models can be set up as a\u00a0software-based\u00a0service\u00a0for the end-user operation and use.\u00a0\u00a0<\/p>\n

<\/p>\n

Conclusion<\/strong>\u00a0<\/p>\n

<\/p>\n

All the above use cases are real-world\u00a0applications\u00a0in the finance sector and its industries where ML and data science are currently being used extensively to leverage profit and improve customer\/user experience. Since the\u00a0platforms where these applications are done are so large that the ML systems need to work and process a\u00a0very large amount of data.\u00a0To run models on such huge data requires\u00a0high-end hardware resources which is not possible on a single machine. This is the reason why using Azure Databricks\u00a0can help. It is a\u00a0cloud-based\u00a0tool for ETL purposes\u00a0and\u00a0allows\u00a0to run of several types of ML applications on its cluster.\u00a0<\/p>\n

<\/p>\n

Azure Databricks uses\u00a0the clustering method. Clusters are a set of hardware resources that are assigned to a user for running the models.\u00a0It is built with the integration of Apache Spark which allows\u00a0parallel processing of multiple\u00a0ML processes and provides the output in seconds.\u00a0Also, the integration of Databricks with Azure cloud helps seamless connection with visualization tools such as\u00a0PowerBI.\u00a0This can help directly build visualizations\u00a0from the outcome of models and can then be used for business decisions with clients and stakeholders.\u00a0\u00a0<\/p>\n

<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t

\n\t\t\t
\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t

\n\t\t\t\t\t\t\tDishant Modi\t\t\t\t\t\t<\/h4>\n\t\t\t\t\t<\/div>\n\t\t\t\t\n\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t

Data scientist intern<\/p>\n\t\t\t\t\t<\/div>\n\t\t\t\t\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t

\n\t\t\t
\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

Machine learning in finance sector:  Machine Learning has penetrated almost every industry and is being extensively used for carrying analytical work which helps the company make important business decisions. Talking about the finance sector, it is a huge industry consisting of insurance, banking, real estate, etc.   There is always data involved with any business and if that data is harvested and put to […]<\/p>\n","protected":false},"author":3,"featured_media":30165,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[97,17],"tags":[95,101],"class_list":["post-8082","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-cloud","category-machine-learning","tag-cloud","tag-macine-learning"],"_links":{"self":[{"href":"https:\/\/ismiletechnologies.com\/en_us\/wp-json\/wp\/v2\/posts\/8082","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ismiletechnologies.com\/en_us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ismiletechnologies.com\/en_us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ismiletechnologies.com\/en_us\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/ismiletechnologies.com\/en_us\/wp-json\/wp\/v2\/comments?post=8082"}],"version-history":[{"count":1,"href":"https:\/\/ismiletechnologies.com\/en_us\/wp-json\/wp\/v2\/posts\/8082\/revisions"}],"predecessor-version":[{"id":30164,"href":"https:\/\/ismiletechnologies.com\/en_us\/wp-json\/wp\/v2\/posts\/8082\/revisions\/30164"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/ismiletechnologies.com\/en_us\/wp-json\/wp\/v2\/media\/30165"}],"wp:attachment":[{"href":"https:\/\/ismiletechnologies.com\/en_us\/wp-json\/wp\/v2\/media?parent=8082"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ismiletechnologies.com\/en_us\/wp-json\/wp\/v2\/categories?post=8082"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ismiletechnologies.com\/en_us\/wp-json\/wp\/v2\/tags?post=8082"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}