Filter by keyword, subject, or both. Updates live as new model answers are added to our portal.
Machine Learning / Data Mining / Text Mining
Machine Learning Analysis of Classification Models and Text Mining on Furniture Review Data
This technical machine-learning report demonstrates the practical application of predictive modelling and text mining using WEKA. The work is divided into two major tasks. The first evaluates and compares Support Vector Machine and Decision Tree classification models, while the second applies text-mining techniques to furniture-review data and compares multiple classifiers after preprocessing, feature selection and class balancing. The first task uses the Screenshots.arff dataset to investigate the performance of libSVM and J48 Decision Tree classifiers. A 70% training and 30% testing split is applied, and the models are manually tuned to examine how different parameter settings affect predictive performance. For libSVM, an RBF kernel is used while different gamma and cost values are tested through grid-search-style experimentation. The report identifies gamma 0.03 and cost 2 as the strongest tested combination, producing approximately 91.67% accuracy on the test split. The J48 model is also optimised by adjusting the confidence factor used for pruning. Several confidence-factor values are examined, with 0.09 producing the strongest reported result of 80% accuracy. The optimised SVM and J48 models are then compared using five-fold cross-validation, where libSVM achieves 89.75% accuracy compared with 81.25% for J48. The second task focuses on text mining of Furniture Reviews. Text preprocessing includes TF-IDF term weighting, stopword removal, stemming, conversion to lowercase and word-count generation. The resulting textual dataset is transformed into a numerical feature representation suitable for machine-learning classification. Dimensionality reduction is performed using InfoGainAttributeEval with Ranker, selecting the 900 most informative attributes. The dataset is then balanced using WEKA techniques including Resample and SpreadSubsample to reduce class bias before classification. Finally, three classifiers—Naive Bayes, libSVM and J48—are evaluated on the balanced text dataset. The reported accuracies are 90.52% for Naive Bayes, 58.62% for libSVM and 78.45% for J48. The analysis concludes that Naive Bayes performs strongest for the processed furniture-review dataset, while the wider exercise demonstrates the importance of preprocessing, parameter tuning, feature selection, class balancing and appropriate model evaluation in producing reliable classification results. Important: this upload appears to be the completed student report, not the actual assessment guideline. Because the document does not state the university, module name, academic level, academic year, required word count or prescribed referencing style, I would leave those fields as Not specified rather than guessing.
Read Model Answer →
Machine Learning / Cloud Computing
3,984 words
Machine Learning on Cloud: Fraud Detection Model Design, Training and Evaluation
This postgraduate group project focuses on the design, development and critical evaluation of a cloud-based machine learning solution for financial fraud detection. The scenario involves a financial services organisation seeking to detect fraudulent transactions in order to reduce financial losses and improve customer security. Students are required to analyse an appropriate dataset, develop a machine learning solution, evaluate its effectiveness and critically consider the suitability of cloud technologies for deployment. The project begins with a cloud feasibility study, requiring critical comparison of at least two major machine learning platforms such as Microsoft Azure, Amazon Web Services and Google Cloud Platform. Evaluation criteria include performance, scalability, cost, compliance, integration and vendor lock-in, followed by a justified recommendation. Students then conduct exploratory data analysis to identify patterns, anomalies and correlations using appropriate visualisations such as heatmaps, histograms and boxplots. A substantial component addresses data preprocessing and class imbalance. Students are expected to clean and transform the data, apply scaling and encoding, perform feature engineering and investigate approaches such as SMOTE, undersampling and cost-sensitive learning. Each preprocessing choice must be justified in terms of its potential impact on model performance. Students must select and train at least two machine learning models, with suggested approaches including Logistic Regression, Random Forest, XGBoost and Neural Networks. Model development incorporates cross-validation and hyperparameter tuning. Evaluation uses fraud-relevant measures including Precision, Recall, F1 score, AUC and precision-recall curves, supported by confusion matrices, ROC curves and feature-importance visualisations. The project concludes with critical consideration of professional and ethical issues in cloud-based AI, including bias, fairness, transparency, data privacy and sustainability. The overall assessment therefore integrates cloud-platform evaluation, machine learning development, imbalanced classification, model evaluation and responsible AI practice. Overview word count: approximately 340 words.
Read Model Answer →
Operations and Supply Chain Management
1,987 words
Supply Chain Analytics and Quantitative Data Analysis for Organisational Decision-Making
This postgraduate individual report focuses on the application of quantitative data analysis to Operations, Logistics and Supply Chain Management decision-making. Students are required to select an organisation from the private, public or third sector and investigate a relevant operational or supply-chain issue using quantitative data. The purpose is to demonstrate how data can be collected, prepared, analysed and interpreted to generate evidence-based insights that may support managerial decision-making. The selected dataset must relate to the organisation's operations or supply chain and may include variables such as revenues, product orders, sales, transportation costs, procurement expenditure, inventory levels or other appropriate quantitative measures. The dataset must contain at least 60 observations, and the analysis must involve at least two variables. Data may be obtained directly from organisations or from recognised secondary-data platforms and databases. The assessment consists of two equally weighted components. Part A – Motivation and Justification for the Analysis requires students to formulate relevant analytical questions and explain their practical importance by linking them to Operations and Supply Chain Management theory and business practice. Appropriate academic, industry and practitioner evidence should be used to justify the selected issue. Research questions may also be translated into testable hypotheses where appropriate. Part B – Execution of the Analysis requires students to answer the identified questions through appropriate statistical techniques. Potential methods include tables, charts, summary statistics, t-tests and regression analysis. Data may first need to be cleaned, transformed and structured before analysis. The results must then be interpreted clearly for a managerial audience such as the organisation's board, owner or CEO. The statistical analysis is expected to be conducted using Stata, with all data-cleaning, manipulation and analytical commands recorded in a reproducible do-file. The report must also demonstrate explicit links between theory and practice and contain a suitable mixture of academic and professional evidence, including at least five academic journal articles. Harvard referencing is required throughout. The resulting work demonstrates practical competence in business analytics, statistical interpretation, supply-chain decision support, reproducible analysis and evidence-based managerial communication. Overview word count: approximately 370 words.
Read Model Answer →
Computer Science / Algorithms and Optimisation
Genetic Algorithms for the Balanced Spanning Tree Problem
This technical research work investigates the Balanced Spanning Tree Problem, an optimisation problem that seeks to construct a spanning tree capable of balancing two competing network objectives: the low overall cost associated with a Minimum Spanning Tree and the short source-to-destination distances provided by a Shortest Path Tree. For an undirected, weighted and connected graph with a designated root vertex, a balanced spanning tree is defined using two parameters, α and β. The first limits the distance between the root and each vertex relative to the corresponding shortest path in the original graph, while the second limits the total tree weight relative to the Minimum Spanning Tree. Finding an optimal balanced spanning tree is computationally challenging because determining whether a graph contains an (α, β)-balanced spanning tree is an NP-complete problem. The research therefore proposes genetic algorithms as heuristic optimisation techniques for two variants of the problem: minimising β while α is fixed, and minimising α while β is fixed. The proposed genetic algorithm represents individual spanning trees as chromosomes composed of graph edges. An initial population of valid spanning trees is generated before evolutionary operations are repeatedly applied. The approach incorporates chromosome selection, crossover, mutation, fitness evaluation and stopping criteria. Four selection strategies are examined: Random Selection, Roulette Wheel Selection, Stochastic Universal Sampling and Tournament Selection. The fitness function is based on the relationship between the Minimum Spanning Tree weight and the total weight of the candidate chromosome. Experimental evaluation is performed using randomly generated weighted graphs containing 6, 10, 15 and 20 vertices. The experiments investigate different values of the balancing parameters, selection mechanisms and population sizes. The implementation uses a population size of 30, a maximum of 300 generations, crossover probability of 0.9 and mutation probability of 0.01 in the principal experiments. The reported results show that the genetic approach can generate high-quality balanced spanning trees and, for the tested instances, produced solutions matching the corresponding optimal balanced spanning trees. The study also examines how balancing parameters and population size influence execution time and convergence, demonstrating the practical use of evolutionary computation for complex graph-optimisation problems.
Read Model Answer →
Global Supply Chain Management / Operations Management
2,494 words
Global Supply Chain and Operations Performance: Company Case Analysis
This Level 7 individual assignment requires students to produce a 2,500-word company case analysis examining an important operations performance issue within a real organisation. Students may select an organisation of any size, type, industry or country and must concentrate their analysis on one operations performance objective: cost, dependability, flexibility, speed or quality. The report requires students to identify the current challenges faced by the chosen organisation in relation to the selected performance objective and critically examine those challenges using relevant operations and supply chain management theories, concepts and analytical tools. Rather than providing only a descriptive account of organisational activities, students are expected to apply appropriate theoretical frameworks to the case and evaluate how these concepts could contribute to improved organisational and supply chain performance. A significant component of the assignment involves critically discussing appropriate best practices for performance improvement. These may include digital technologies, sustainability practices or other relevant operational and supply chain approaches. Students should connect these practices directly to findings from their chosen company case and assess their practical relevance, opportunities and limitations. Academic literature and appropriate real-world evidence should be used throughout to substantiate the analysis and recommendations. The assignment evaluates students' ability to analyse supply chain and operations problems, apply academic theory to organisational practice, and develop evidence-based conclusions and practical recommendations. The marking rubric places substantial emphasis on analysis and discussion (30%), application of theory (30%), and conclusions and recommendations (30%), with the remaining 10% allocated to presentation, logical structure, English expression and correct referencing. The report must use Harvard referencing, include a contents page, and follow the specified academic formatting requirements, including Arial size 12, 1.5 line spacing and A4 pages with 2.54 cm margins.
Read Model Answer →
Marketing
4,000 words
Strategic Recovery Marketing Report — Diagnosing Underperformance and Building a Sustainable Turnaround Plan
This is a case-based marketing assessment in which the student selects a real business that is currently underperforming or failing, diagnoses the causes, and builds a full marketing recovery strategy for it. The company choice is the student's own but requires module team approval, so the selection itself carries risk: a firm with thin public disclosure will starve the analysis, while an over-documented household name invites description rather than diagnosis. The deliverable is a formal report of around four thousand words, excluding references and appendices, referenced in APA 7. Appendices can carry supporting data, models and supplementary analysis, but not core content — a common way marks are lost is pushing substantive argument into an appendix to stay within the word limit. The report has two linked halves that students often treat as separate. The first is diagnostic: why is this business underperforming? This demands explicit application of marketing theory rather than a narrative of the company's troubles assembled from press coverage. The second is prescriptive: a recovery strategy that follows from the diagnosis. Recommendations that could have been written without the analysis — refresh the brand, invest in digital, improve customer experience — score poorly regardless of how well they are expressed. Where this module differs from a generic strategic marketing assessment is the sustainability and ethics dimension. The learning outcomes centre on sustainable marketing, social responsibility, and the intersection of marketing technology with sustainable practice. The marking criteria reward conclusions that show awareness of ethical and sustainability dimensions at every band above a pass. A recovery plan built purely on cost and revenue logic will therefore underperform against the rubric even if it is commercially sensible. The strongest submissions treat sustainability as part of the recovery mechanism rather than a section appended at the end. Assessments of this type increasingly sit within a tiered AI policy. Where a permissive tier applies, students may use AI tools for idea generation, structuring, source discovery, summarising notes, and proofreading or feedback — but not for producing the analysis itself — and must declare which tools were used and how, usually in a table placed before the reference list. Students are also expected to retain evidence of how their thinking developed, such as version histories or drafts, which can be requested if misconduct is suspected. Our support on assessments of this type is guidance-based. Typical areas of help include: advising on company selection and data availability, explaining how a diagnostic framework should structure an argument, showing the difference between descriptive and evaluative use of theory, clarifying how sustainability criteria are actually assessed in a marking rubric, checking APA 7 consistency, and reviewing a completed draft against the published criteria.
Read Model Answer →
Entrepreneurship and Business Start-up
5,000 words
Enterprise Start-up Portfolio — Business Plan, Fundraising Strategy and Entrepreneurial Self-Assessment
An enterprise start-up portfolio assessment asks students to originate a business idea and build the full supporting case for it, then present that case both in writing and as a recorded investor pitch. It is a pass/fail module structure in which every component must be passed individually — a strong business plan cannot compensate for a weak pitch, or vice versa. The written portfolio divides into two unequal halves. The larger part is the business plan itself, built to a fixed section structure with prescribed word allocations: an executive summary; the business idea set against an identified market gap, with market research and competitor analysis; customer profiles and segmentation; product development; marketing and communications; financials and business models covering costing, pricing, sales and revenue; and the founding team with its core competencies. The word allocations are not decorative — financials carry the single largest weighting in both the word budget and the marking rubric, which tells students where analytical depth is expected and where concision is. The smaller part is reflective. It covers the fundraising strategy — which funding sources are realistic for this venture, and how each would be targeted, approached and secured — and the student's own entrepreneurial tendency, informed by a standardised self-assessment instrument taken online. The rubric here rewards critical self-reflection over description: reporting a test result scores poorly; interpreting what the result means for how this founder should build a team and where they need support scores well. The pitch component is assessed on visual and audio quality, content and message, comprehension, delivery, and evident preparation. Technical execution carries real marks, which students routinely underestimate. Two things separate strong submissions. The first is internal consistency: the revenue model must follow from the pricing, the pricing from the customer segment, the segment from the identified gap. Plans that read as seven separate essays under seven headings lose marks even when each section is individually competent. The second is specificity in the financials — costing assumptions stated and justified, rather than round numbers presented without derivation. Note that assessments of this type commonly require the student to retain all drafts and earlier versions of their work, and to sign a detailed declaration itemising exactly how any AI tools were used. Our support on assessments of this type is guidance-based. Typical areas of help include: explaining what a market gap argument needs to be credible, showing how competitor analysis should be structured rather than listed, clarifying how costing and pricing assumptions should be built and presented, reviewing whether a fundraising strategy matches the venture's actual stage, explaining how reflective writing is assessed at postgraduate level, and checking a completed draft against the published rubric.
Read Model Answer →
Operations and Supply Chain Management
1,800 words
Strategic Sourcing and Supply Chain Resilience Under Global Uncertainty — A Firm-Level Critical Evaluation
This type of postgraduate coursework asks students to take a single real firm — a British company, or a multinational with substantial UK operations — and critically evaluate how its sourcing and supply chain strategy has adapted to a decade of sustained disruption: the pandemic, geopolitical conflict, tariff volatility, and departure from the European single market. The analytical scope is broad but the depth expectation is narrow. Students choose one or two themes rather than surveying all of them: insourcing versus outsourcing and location decisions; single versus multi-sourcing across supplier segments or regions; how supplier selection and monitoring criteria have shifted toward reliability and geographic proximity; alignment between sourcing decisions and wider corporate objectives; supplier and customer relationship management under cross-border friction; inventory tactics such as stockpiling and safety stock repositioning; digital adoption for visibility and compliance; sustainable sourcing under cost pressure; or risk management around currency, customs and compliance. The evidence base is deliberately mixed. Alongside academic literature, students are expected to draw on annual reports, shareholder briefings, company statements, practitioner journals and recent news coverage — with a minimum spread of credible sources across both categories, and some of the non-academic material drawn from the most recent year so the analysis reflects current firm behaviour rather than historical commentary. At least one theoretical framework from the module or the wider literature must be applied to the firm's decisions, and at least one recent documented practice must be examined with specific sourcing. Two requirements distinguish strong submissions. The first is criticality: the brief explicitly separates evaluation from description, and marks weight critical analysis most heavily. Reporting what a firm did is not the task; assessing whether it was the right response, and what opportunities and risks it created, is. The second is the recommendation — at least one specific, actionable proposal with steps, anticipated obstacles, expected outcomes, and a clear line back to the firm's own stated goals. A generic suggestion to "diversify suppliers" fails this test; a costed, sequenced proposal grounded in the firm's actual constraints does not. Word-count conventions are stricter than students often expect: in-text references, tables, illustrations and front matter typically count, while appendices and the reference list do not. Our support on assessments of this type is guidance-based. Typical areas of help include: narrowing a firm and theme so the analysis fits the word limit, explaining the difference between description and critical evaluation with worked examples, clarifying how a theoretical framework should structure an argument rather than sit decoratively in a paragraph, checking source mix and Harvard referencing consistency, and reviewing a completed draft against the published assessment weightings.
Read Model Answer →