Was a website redesign successful? Multivariate test
Was a website redesign successful? Multivariate test

DataCamp Competition submitted on 03-Feb-22

A/B testingMultivariate TestingHypothesisStatistical PowerPython
Modelling Lottery Number Popularity
Modelling Lottery Number Popularity

Which numbers are how popular among the mean lottery participant to be picked on their tickets? + In case that someone has a winning game, one really might want to be able to predict the profit share quota, being directly dependant on the popularities of the numbers being drawn.

PythonScikit-learnRegression
Can you help reduce employee turnover? Employee Churn Analysis
Can you help reduce employee turnover? Employee Churn Analysis

DataCamp Competition - employee turnover submitted by me on 20-Feb-22

Churn AnalysisRetentionHypothesisStatisticsPython
Trends on Data Science Question Topics 2021

Explore Data Science Question Data of the Data Science Stack Exchange (DSSE) and analyze trends and topics such as Deep-Learning over time with pandas and Association Rules with library mlxtend.

SQLAssociation RulesAprioriData Wrangling
Tableau Analysis Story of Databel Customer Churn
Tableau Analysis Story of Databel Customer Churn

Analysed the structure of churn of customers in Databel telco company

TableauChurn Analysis
Udacity AB testing Online Experiment Design and Analysis - Final Project in Python
Udacity AB testing Online Experiment Design and Analysis - Final Project in Python

AB testing Experiment Design Project

AB testingUdacityHypothesisExperiment DesignPython
Client Segments Data Simulation & Cost Sensitive Multi-classification
Client Segments Data Simulation & Cost Sensitive Multi-classification

In this notebook we opt to interpret the given client segmentation model and generate our own data based on our assumptions and a modest variety of features and limited knowledge about the differences of these segments

market segmentationdata generationdata simulationclassificationcost-sensitiveLogistic RegressionSVMPython
Predictive Maintenance ~ failure prediction with binary classification implemented as Gated Recurrent Units Recurrent Neural Network
Predictive Maintenance ~ failure prediction with binary classification implemented as Gated Recurrent Units Recurrent Neural Network

In contrast to earlier survival analysis we apply a more performant (reliable) solution in detecting degradation in the jet engines conditions. The sensor measurement data will be arranged in time series windows for binary classification training of our predicitive maintenance model.

Predictive MaintenanceTime SeriesclassificationDeep LearningRecurrent Neural NetworkGated Recurrent UnitsTensorflowPythonGRURNN
Understanding the local electricity market - Data Analysis & Forecast
Understanding the local electricity market - Data Analysis & Forecast

This Challenge has been originally a DataCamp Competition in April 22 and due for May 22, in which I could not participate in time. I bookmarked it for later - so here we go a few weeks later answering the challenge questions, this not just maximising the ML performance/forecast accuracy. Your company's pricing committee wants your team to estimate energy prices for the next 12-18 months to use those prices as the basis for contract negotiations. Let's do that.

Time SeriesMarket AnalysisEnsemble LearningRegressionStatsmodelsDatacamp ChallengePython
Optimizing Online Sports Retail Revenue (SQL Analysis Project)
Optimizing Online Sports Retail Revenue (SQL Analysis Project)

In this notebook, we play the role of a product analyst for an online sports clothing company. The company is specifically interested in how it can improve revenue. We will dive into product data such as pricing, reviews, descriptions, and ratings, as well as revenue and website traffic, to produce recommendations for its marketing and sales teams.

SQLAnalysisCommon Table ExpressionAggregationCorrelationCASEDatacampPython