Academic Model Answers
Library for UK Postgraduates

Browse tutor-verified model answers across MBA, Law, Finance, Research Methods and more. Use as study references for your own work.

247 model answers 30+ subjects covered 50+ UK universities
Find your assignment

Search the Library

Filter by keyword, subject, or both. Updates live as new model answers are added to our portal.

Filtering by “Google Colab” Clear filters

Available Model Answers (5)

Real-time Database Sync
Research Methods

Assignment 3 – Large Language Models: LLM Coding and Report

This individual assessment for the Research Methods module focuses on the application of Large Language Models (LLMs) to a practical data science problem. The assignment is worth 25% of the module and is designed to develop students’ knowledge and understanding of research methods, investigative planning, data analysis, model evaluation and effective technical communication. Students are required to complete both a coding component and a concise written report demonstrating how an LLM has been selected, trained or fine-tuned, applied to a suitable task and evaluated against an appropriate baseline. The assessment begins with familiarisation with relevant literature. Students are expected to investigate the history and development of their chosen problem and examine the methods that have previously been used to address it. The brief provides key papers on common types of LLMs as a starting point for the literature review. Students then select a task that can be addressed through fine-tuning an LLM, with examples including sentiment analysis, fake news detection and topic classification. A publicly available dataset suitable for the selected text-classification problem must also be identified. Suggested sources include Kaggle and Hugging Face Datasets. The data must be appropriately preprocessed, including tokenisation using BERT's tokenizer and division into training and testing sets. Students then fine-tune a pre-trained BERT or BERT-style model using suitable tools such as the Hugging Face Transformers library and PyTorch. Possible model choices include BERT, RoBERTa and T5. The selected model should be appropriate for the specific problem, recognising that different language models may perform differently across tasks. Students are expected to implement a suitable training process using an appropriate optimiser and loss function. Model performance must be evaluated using relevant classification metrics, including accuracy, precision, recall and F1-score. The performance of the selected LLM should also be compared with a baseline model, such as Logistic Regression, Naive Bayes or a pre-trained BERT model. The analysis should explain the results and consider their relevance to the chosen problem. Two main submission components are required. The first is a code notebook, such as a Jupyter or Google Colab notebook, containing annotations explaining the purpose and operation of the relevant code so that another person can understand and reproduce the work. The second is a report of no more than three pages, including appropriate figures, tables and references. The report should cover the motivation and dataset, methodology, model training and evaluation, results and discussion, limitations, conclusion and possible future improvements. The assessment rubric places particular emphasis on coding quality and implementation, model architecture, analysis and interpretation, and report presentation. Strong work should demonstrate well-structured and reusable code, clear explanation of the model architecture and configuration, appropriate evaluation metrics and visualisations, meaningful comparison with relevant literature or baseline models, and critical evaluation of the model's success and possible improvements.

Read Model Answer →
Data Science 1,000 words

Individual Project – Image Segmentation

This individual project focuses on image segmentation using a subset of the ADE20K dataset. The assessment requires students to investigate viable image segmentation models, analyse and visualise the provided data, develop appropriate data preprocessing procedures, train a segmentation model and critically evaluate the resulting performance. The assignment is worth 25% of the module assessment and is designed to assess students’ ability to apply research methods to a data science problem, communicate analytical findings effectively and select appropriate methods while understanding their advantages and limitations. Students are required to work with the provided ADE20K dataset and produce a model capable of semantic segmentation for four specified object classes: person, car, book and airplane. The model must identify which regions of an unlabelled image correspond to these four classes. The assignment specifically requires semantic segmentation rather than simply identifying whether an object is present. Treating the task as binary segmentation, where all objects are considered a single foreground class, will result in a significant penalty. The project requires students to investigate different approaches and models, perform exploratory data analysis, develop suitable preprocessing procedures and customise their selected model or models to improve performance. Students may use more than one model, although at least one model must be partially or fully trained by the student. Where multiple models are used, comparison with pretrained models is encouraged. Potential approaches include segmentation architectures such as U-Net and Mask R-CNN, with appropriate model selection justified through relevant literature and experimental evidence. The report should contain at least four core sections: an Introduction incorporating a literature review, Data Description and Exploratory Data Analysis, Methodology, and Results and Discussion. The literature review should cite at least three relevant research papers. The results section should include evaluation of three test images using the developed model and comparison with relevant published literature. Students are expected to provide a critical analysis of their work rather than simply reporting numerical results, explaining the reasons for observed outcomes and considering how modelling and implementation choices affected performance. The assessment also requires a documented Google Colab notebook containing the implemented steps used to train and evaluate the model. The notebook should be accessible to markers and should demonstrate the preprocessing, model development, training and evaluation process. The report must be between 700 and 1,000 words, excluding references and code, and should include code in text format as an appendix rather than screenshots. Figures and tables should have clear captions explaining what they present and their source. Assessment criteria include literature review and context, dataset description and exploratory data analysis, implementation quality, quality of analysis and critical discussion, and report quality and structure. Strong work is expected to demonstrate appropriate model selection, effective preprocessing and augmentation, suitable evaluation metrics such as Intersection over Union (IoU) and Dice score, meaningful visualisation and a critical interpretation of results and limitations.

Read Model Answer →
Data Management / Business Analytics 2,500 words

Data and Decision Making (BS776) — Business Report: Two-Source Data Analysis in Python for Evidence-Based Decision-Making

This Level 7 report applies data management theory to a self-selected industry problem and carries it through to a working Python analysis and a defensible business recommendation. The brief is deliberately open on sector — finance, healthcare, transport, cyber security, business intelligence and others are all permitted — but firm on one point: the chosen topic must carry a genuine business implication rather than being a purely technical or clinical analysis. The work therefore begins by framing a specific data-driven decision the organisation needs to make, and returns to that decision at every stage. Two distinct data sources are then identified from approved open repositories and critically evaluated side by side. The evaluation covers the data types each holds, how the data was collected and what bias that introduces, how each is stored and managed, and where the weaknesses lie — proposing concrete data management solutions for the problems identified rather than simply cataloguing them. The analytical core examines, transforms and explores both datasets using univariate and multivariate techniques. All work is carried out in Python within Google Colab, with full screenshots of the code and outputs placed in the appendices and the live Colab link shared for verification. Charts and tables sit in the main body where they support interpretation, each labelled and referenced back to its data source, and each appendix is cited from the narrative so the reader can move between argument and evidence. Data cleaning and transformation steps are shown and justified, not glossed. Findings are reported at length and converted into a clear recommendation covering both the immediate decision and the current and future direction of data management for the business. The limitations section is written honestly — sample coverage, data recency, the assumptions the transformation forced, and what the proposed solution cannot address. Running alongside this, the module's weekly consolidation discussions are evidenced. Five or more critical responses across units two to nine are screenshotted, dated, individually labelled as appendices, and each supported by academic and practice references. Crucially, these are not left sitting in the appendix: they are cited and used within the main body to support the critical discussion, which is where the marks for that component sit. The report follows the prescribed structure — title page, executive summary, contents, introduction, main section with subsections per task, findings, recommendations, limitations, conclusion, Harvard reference list and full appendices — submitted as a single file.

Read Model Answer →
Machine Learning / Data Science

Linear Regression and Stability of the Moore–Penrose Pseudoinverse Using Python

This machine learning practical and assessment activity develops an understanding of linear regression, Ordinary Least Squares and the Moore–Penrose pseudoinverse using Python. The work progresses from generating synthetic regression datasets to implementing regression algorithms manually, applying established machine learning libraries, analysing real datasets and evaluating the stability of estimated regression coefficients. The laboratory component begins with the generation of synthetic linear regression data using NumPy, including explanatory variables, random noise and an outcome variable. Students then implement simple linear regression without relying on machine learning libraries, using the least-squares solution to estimate the intercept and slope. The resulting observations and fitted regression line are visualised using Matplotlib. The work is subsequently extended to multiple linear regression, where several independent variables are used and coefficients are first calculated manually before the same problem is solved using Scikit-learn. The laboratory also introduces application of regression to the Scikit-learn Diabetes dataset, including feature and target standardisation, model fitting, prediction, correlation analysis and interpretation of regression coefficients. It also highlights the importance of residual analysis when assessing whether a linear model is appropriate. The associated weekly challenge focuses on the stability of linear regression solutions estimated using the Moore–Penrose pseudoinverse. Using a house-price dataset containing variables such as property size, number of bedrooms, distance from the city centre and property age, students construct the design matrix, standardise features and the response variable, and calculate regression coefficients using the pseudoinverse. Students then investigate model robustness by repeatedly fitting the regression model to random subsamples of different sizes and analysing the mean and standard deviation of each coefficient. Tables, boxplots or error-bar visualisations can be used to compare coefficient variability. The final discussion considers which variables are most influential, which coefficients are most stable, how sample size affects stability and whether coefficient interpretation remains reliable across different samples. The final work is submitted as a single PDF exported from Jupyter Notebook or Google Colab, combining documented Python code, experimental results, plots and written interpretation in a professionally organised notebook. Overview word count: approximately 360 wor

Read Model Answer →

Assignment 2 - Individual project Image segmentation

Assignment tasks This assignment will focus on Image Segmentation using the ADE20K dataset. This is an individual assignment where each student will produce a report on the data analysis they will perform. You are encouraged to utilise Google Colab for the coding part of your assignment. https://herts.instructure.com/courses/129101/assignments/406384 1/86/17/26, 12:10 PM Assignment 2 - Individual project - Image segmentation - 25% You will explain and discuss the data processing, the method(s) you make use of and elaborate the outcome. You will work on the ADE20K dataset (explained below in more detail) to research viable models to train, discuss different approaches to explore and visualise the data (i.e., perform EDA), build a tool to pre-process the dataset, and customise your chosen model(s) to improve performance. You will produce a code that does semantic segmentation of the 4 classes targeted in this assignment: person, car, book, airplane. In more detail, your model(s) should identify which of these 4 classes the region of the image corresponds to, and should be applicable to any unlabelled image. To be clear: doing only binary segmentation (i.e. any class vs background) will result in a very large penalty, as you will be considered not to have done the required task. You may use more than one model, but one has to be trained partially or fully by you. Should you use more than one, you are encouraged to compare your main trained model with one or more pre-trained models.

Read Model Answer →