It is important that credit card companies are able to recognize fraudulent credit card transactions so that customers are not charged for items that they did not purchase. Content The dataset contains transactions made by credit cards in September 2013 by European cardholders. This dataset presents transactions that occurred in two days, where we have 492 frauds out of 284,807 transactions. The dataset is highly unbalanced, the positive class (frauds) account for 0.172% of all transactions. It contains only numerical input variables which are the result of a PCA transformation. Unfortunately, due to confidentiality issues, we cannot provide the original features and more background information about the data. Features V1, V2, … V28 are the principal components obtained with PCA, the only features which have not been transformed with PCA are 'Time' and 'Amount'. Feature 'Time' contains the seconds elapsed between each transaction and the first transaction in the dataset. The feature 'Amount' is the transaction Amount, this feature can be used for example-dependant cost-sensitive learning. Feature 'Class' is the response variable and it takes value 1 in case of fraud and 0 otherwise. Given the class imbalance ratio, we recommend measuring the accuracy using the Area Under the Precision-Recall Curve (AUPRC). Confusion matrix accuracy is not meaningful for unbalanced classification. Update (03/05/2021) A simulator for transaction data has been released as part of the practical handbook on Machine Learning for Credit Card Fraud Detection - https://fraud-detection-handbook.github.io/fraud-detection-handbook/Chapter_3_GettingStarted/SimulatedDataset.html. We invite all practitioners interested in fraud detection datasets to also check out this data simulator, and the methodologies for credit card fraud detection presented in the book. Acknowledgements The dataset has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Université Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the DefeatFraud project Please cite the following works: Andrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015 Dal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon Dal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE Dal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi) Carcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-Aël; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier Carcillo, Fabrizio; Le Borgne, Yann-Aël; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing Bertrand Lebichot, Yann-Aël Le Borgne, Liyun He, Frederic Oblé, Gianluca Bontempi Deep-Learning Domain Adaptation Techniques for Credit Cards Fraud Detection, INNSBDDL 2019: Recent Advances in Big Data and Deep Learning, pp 78-88, 2019 Fabrizio Carcillo, Yann-Aël Le Borgne, Olivier Caelen, Frederic Oblé, Gianluca Bontempi Combining Unsupervised and Supervised Learning in Credit Card Fraud Detection Information Sciences, 2019 Yann-Aël Le Borgne, Gianluca Bontempi Machine Learning for Credit Card Fraud Detection - Practical Handbook

AdventureWorks is a fictitious multinational manufacturing company. The data set used for this report is from the AdventureWorks2014 version. The goal of this project is to demonstrate how building powerful and beautiful (I hope :)) reports in Power BI by following the data visualization best practices and the data modelling patterns, showing the awesome features of Power BI like Report Page Tooltip, Calculated Groups, Forecasting, What-If parameters, Time Intelligence Functions, complex DAX code, custom charts and how it is easy to integrate Power BI with Python/R script in order to build machine learning models and so creating advanced and predictive analytics reports. Reports Pages are as follow: - P&L Overview: Profit & Loss Report, in which I analyzed the economic status of the company from the point of view of Revenues and Expenditures. In this report page I compared the trend of actual amount and budget amount, unfortunately for 2011 year only (missing data for other years). You can notice the powerful feature of “report page tooltip” in this page, by hovering over the bar charts. - Internet Sales Overview: in this report page I analyzed the sales of products to customers via Internet. You can notice the forecasting feature of Power BI and the use of what-if parameters in order to build advanced analytics reports. Also I made use of calculated groups (for further info about visit https://www.sqlbi.com/articles/introducing-calculation-groups/). - Reseller Sales Overview: similar to the previous one, but this time the focus is on the sales of products to resellers. Things to notice in this report page are the comparison of current sales vs last year sales, the comparison of actual sales amount vs budget/quota sales amount, and the running total and moving/running average charts. - Product Inventory Overview: inventory management analysis of the company. I analyzed the current stock on hold vs the recent sales revenue, showing the value of current stock, the current units in stock and the stock ratio. - Products Overview: in this report page I analyzed the products by category, color, size, “ABC” class too. Two very interesting and powerful things to notice: the basket analysis using DAX and the basket/association rules analysis using R script and apriori machine learning model. I made use of the custom chart called “Network Chart” to represent the association rules between products. Through the basket analysis the user could know which product is likely to be bought with another one. - Customers Overview: customer analysis by age group, location, status, and so on. The customer could be classified as “Bike Buyer” and “Non Bike Buyer”. So I decided to build a machine learning model (in this case I used XGBoost algorithm in Python) in order to predict if a (new) customer would be a bike buyer or not. The model has a prediction accuracy of about 84% which it is not bad. - Employees Overview: employee analysis by sales location, title, age. Thing to notice is the ribbon chart through which I can analyze the performance of employees over time. - Reseller Overview: analysis of the performance of the resellers. Important dimensions to analyze are the business type, the product line, the reseller location.

Tech career has taken over the world with an exponential increase in opportunities in the job market. Niche fields like data science and cybersecurity are booming with hefty salary packages. Every industry in the world is facing some technological disruption degree but, Information Technology is a diverse industry that can take careers in n number of directions. Which career path to follow in the world is not an easy determination? Here are the top 10 tech careers in Australia that are booming and taking off now, according to the Asia-Pacific Tech and Executive Talent Specialists Findings. Java, Python & GoLang Developers Their primary platforms work well with algorithms required to operate or build AI functionalities and Machine Learning. So they are in current top trends now. Experts in these are difficult to find by as the experience is mostly coming from the startup space, not from the larger employers. JavaScript Developers (with Angular or React Expertise) JavaScript Developers are among the top 10 tech careers in Australia. It’s a versatile language used across a variety of businesses so will continue to be in demand for their talents. The larger number of frameworks within the language makes it a talent pool segmented across niche expertise. DevOps (Cloud) & DevSecOps (Security) & Cloud Security Engineers These are required to maintain and automate the developer’s environment. It’s growing as businesses are becoming more reliant on high volumes of data. DevOps engineers speed up the deployment rate and ensure the minimal downtime of products. DevSecOps Engineers perform same with a focus on security code level security. Cloud Security Engineers instruct on maintaining the quality of coding methods which promote a secure cloud-based environment. Cyber Threat Intelligence / Cyber Emergency Response (CERT) Managers These specialists act as a bullet in the world of cyber attackers. They identify and mitigate risk and respond to cyber-attacks allowing businesses to maintain service, productivity, and data security. Automation Engineers They speed up the market and reallocate the resources by automating human capital savings and processes saving cost. Data Scientists These jobs are booming as businesses seek to better understand and derive value from the data they have generated from their customers. More enterprises are consequently turning to data scientists to apply data-driven strategy decisions and allocate resources more efficiently for a better forecast. Data Engineers They are the critical members for an enterprise as a data analytics team. Their demand is high as more and more businesses are becoming reliant on manipulation and collection of high volumes of data. Agile Coaches / Scrum Masters They are responsible for teaching and running methodological processes and frameworks in the search for efficiency. So demand for these roles will continue to grow. CX/UX Researchers and Designers They are responsible for collecting and making design decisions based on customer experience data and allow the businesses to create better efficiencies across the organization by optimizing their product to something that serves the requirements of the customers. Tech Sales Executives (Enterprise Level) Enterprise-level Tech Sales Executives will always be in demand as they are responsible for an efficient path towards the capital growth of the business. The salesperson who can build strong relationships and grow steadily are in constant demand.

A major gas and electricity utility that supplies to corporate, SME (Small & Medium Enterprise), and residential customers. The power-liberalization of the energy market in Europe has led to significant customer churn, especially in the SME segment. They have partnered with us to help diagnose the source of churning SME customers.

It is no wonder that how our favorite coffee shop Starbucks employs data analytics and business intelligence techniques to deliver excellent customer service. This is the largest and famous coffee chain which has become one of the places which uses data analytics and enterprise applications in intersection. This report illustrates how behind a freshly prepared cup of coffee there is an insightful corporate tactic and how factors like weather conditions and twitter sentiments affect the location and stocks of Starbuck stores. Predicting stock prices based on twitter sentiments data would produce strong buy or not is still a debatable topic over the years and making it more difficult to forecast accurately. Data analytics also plays a key role in determining the best location for new stores. In this study, for data extraction APIs were used to extract Twitter Sentiment and weather condition and Starbucks Location dataset was taken from Kaggle in csv format. After Data Transformations and Data Loading, a data warehouse was created for further analysis. Using our analysis, a significant dependency of all these datasets is identified using python libraries. For data storage MongoDB and SQL were used.It is no wonder that how our favorite coffee shop Starbucks employs data analytics and business intelligence techniques to deliver excellent customer service. This is the largest and famous coffee chain which has become one of the places which uses data analytics and enterprise applications in intersection. This report illustrates how behind a freshly prepared cup of coffee there is an insightful corporate tactic and how factors like weather conditions and twitter sentiments affect the location and stocks of Starbuck stores. Predicting stock prices based on twitter sentiments data would produce strong buy or not is still a debatable topic over the years and making it more difficult to forecast accurately. Data analytics also plays a key role in determining the best location for new stores. In this study, for data extraction APIs were used to extract Twitter Sentiment and weather condition and Starbucks Location dataset was taken from Kaggle in csv format. After Data Transformations and Data Loading, a data warehouse was created for further analysis. Using our analysis, a significant dependency of all these datasets is identified using python libraries. For data storage MongoDB and SQL were used.

Designed a prototype of a market basket analytics system, look at the products the customer has in their online shopping cart and recommend another product.