This comprehensive backtesting framework represents a sophisticated analytical tool designed specifically for institutional fixed-income trading strategies focused on Agency MBS markets.

This document is a Repertory Grid Analysis of Innovation Management methods.

Quantum Chromodynamics (QCD) is the quantum field theory that describes the strong nuclear force, one of the four fundamental forces in nature. QCD governs the interactions between quarks and gluons, which are the fundamental constituents of protons, neutrons, and other hadrons.

This document presents a mathematical proof of key concepts in Quantum Field Theory (QFT), demonstrating how quantum fields emerge from the marriage of quantum mechanics and special relativity. We provide both theoretical derivations and computational implementations in R to illustrate the mathematical structure underlying particle physics.

This comprehensive analysis develops a machine learning framework for insurance fraud detection, a critical challenge in the insurance industry where fraudulent claims cost billions annually. Using the Ideal Insurance dataset containing 100,000 claims records, we implement a systematic approach combining exploratory data analysis, advanced feature engineering, and gradient boosting algorithms.

This report presents a fuzzy seismic fragility analysis of gravity dams considering spatial variability of material parameters. The analysis implements fuzzy logic approaches to determine damage state probabilities under various seismic intensity measures. The methodology is based on the paper “Fuzzy seismic fragility analysis of gravity dams considering spatial variability of material parameters” and implements fuzzy intervals, membership functions, and fragility curve generation.

This document analyzes options market data for the S&P 500 index during the 2006-2008 period, focusing on the Global Financial Crisis, using methods similar to David Bates’ 1991 study.

The objective of this project is to analyze the rental prices of furnished apartments in comparison to unfurnished ones. This analysis performs multiple regression analysis, builds functions to represent rental prices, includes furniture as a dummy variable, and illustrates the results. Some apartments are comparable with each other due to location, size, and year of construction. This analysis will help understand the premium associated with furnished apartments.

This analysis examines the potential impact of the BEFIT reform on the tax liabilities of the BMW Group and its subsidiaries.

A solution for creating balanced syndicate groups based on multiple criteria. The algorithm considers several important balancing factors. Balanced syndicate groups are strategically formed teams that maximize internal diversity while ensuring equitable distribution of characteristics across all groups. This approach creates teams with varied perspectives internally, yet maintains overall parity between different teams' collective attributes and capabilities.

The goal of this analysis is to develop a robust, data-driven approach to predict house prices in King County accurately. By leveraging machine learning techniques, we aim to create a model that can process the complex dataset, identify key price determinants, and provide reliable price estimates. This tool would be valuable for real estate professionals, potential buyers and sellers, and financial institutions in making informed decisions about property transactions and valuations.

What is the true significance of geopolitical risk in explaining movements in oil prices? Does Geopolitical Risk in the Middle East and North Africa have a stronger relationship with oil prices, than geopolitical risk in the non-Middle East and non-North Africa sectors of the world?

This document details a comprehensive quantitative analysis of how diffusion processes influence the adoption of renewable energy policies (REPs) by states from 1990 to 2019. The research utilizes six primary datasets and constructs 15 spatiotemporal autoregressive models (five for each of three phases spanning different time periods). The results, presented in tables and figures, gauge the significance of these variables in predicting Renewable Energy Policy adoption across countries and time, offering insights into the interdependencies and mechanisms behind the global spread of renewable energy policy.

EV Customer Detection from Electricity Consumption

Analysis of risk factors for coronary heart disease.

This document is an exploratory data analysis (EDA) report focusing on the classic "mtcars" dataset. The study systematically applies univariate, bivariate, and multivariate analytical techniques to investigate the relationships among automobile characteristics such as weight, horsepower, number of cylinders, and miles per gallon (MPG). Through a combination of data visualization and statistical modeling in R, the report demonstrates how individual and combined vehicle features impact MPG. Findings highlight that car weight and horsepower are the strongest predictors of MPG.

This document presents a statistical analysis of a multi-year, multi-country dataset covering life expectancy and a broad set of health, development, and socioeconomic indicators (such as mortality rates, health spending, vaccination rates, disease prevalence, GDP, and schooling).

The objective is to predict how many patients will visit the walk-in center each day in the next week. The center is open 7 day a week.

Statistical Analysis of Environmental Social Governance Scores by Enterprise State Ownership and Corruption Perceptions Index Rating

This document methodically guides readers through each stage of a machine learning project, from problem definition and data preparation to model development and evaluation, with detailed programming examples using R.

This document presents a statistical analysis examining the relationship between traffic volume and pollutant loads in stormwater runoff at three Denver-area locations: Lakewood Gulch, Weir Gulch, and Sanderson Gulch. The study uses linear regression modeling to correlate total antecedent traffic volume and storm regimes with the mass flow rates and concentrations of five heavy metal pollutants.

This document presents a comprehensive market basket analysis to evaluate whether Blackwell Electronics should acquire Electronidex, a start-up electronics retailer. Using association rules mining (ARM) with the Apriori algorithm on 30 days of transaction data from 9,833 customer purchases across 125 products, the analysis reveals key purchasing patterns including strong associations between desktop computers (particularly iMacs), laptops (especially HP models), and various accessories.

This document presents a comprehensive machine learning analysis to predict sales volumes for new electronic products across four categories: PCs, Laptops, Netbooks, and Smartphones. Using historical sales data from existing products, the study employs exploratory data analysis, feature engineering, and outlier removal to identify that 4-star customer reviews and positive service reviews are the strongest predictors of sales volume.

This document, "ContextBase - Topic Modeling," details a comprehensive workflow—authored and programmed by John Akwei—for applying topic modeling techniques to a large Yelp customer review dataset using the R programming language. It addresses the challenge of extracting actionable insights from vast, complex, text-based business data by leveraging machine learning and natural language processing to automatically identify key themes in customer feedback.

This document, "ContextBase - Sentiment Analysis," authored and programmed by John Akwei, presents a practical workflow that leverages R for performing sentiment analysis on a large dataset of Yelp customer feedback. It addresses the challenge of analyzing vast, unstructured business text data by applying natural language processing and machine learning techniques to efficiently extract, visualize, and quantify customer sentiments, attitudes, and emotional tones.

This document, "Pattern Matching of Time Series Data" by John Akwei, provides a step-by-step example (using R) of how to detect and analyze recurring patterns in historical time series data, specifically the S&P 500 (SPX) index from 2000 to 2018. The workflow covers data import, visualization with candlestick charts, calculation of distances between a recent data segment (query) and earlier periods (reference) to find similar historical patterns, and subsequent plotting and statistical comparison of these matching periods.

This document, "Bank Marketing Data Classification" by John Akwei on RPubs, demonstrates the process of using R programming and data science techniques to classify bank marketing data, specifically targeting whether customers will subscribe to a term deposit.

The document "Dollar Cost Averaging Vs. Technical Indicators ETF Strategies" by John Akwei on RPubs presents a comparative analysis of investment strategies for trading Exchange Traded Funds (ETFs). It involves backtesting both Dollar Cost Averaging (DCA) and various technical indicator-based strategies, evaluating their effectiveness and performance.