Applied Modelling and Visualisation CW1 Coursework Summative Assessment Brief | BPP

Fail 

0-39%

Marginal Fail 40-49%

Pass 

50-59%

Merit 

60-69%

Distinction 

70-79%

High Distinction 80-100% 

Provided data-driven solution fails to execute, fails to  display the options, or  halts during execution.

The data-driven  solution showed inadequate demonstra tion of implicitknowledge base with  some omissions  and/or lack of theory  relating to the use of  ETL processes. No  discussion of ambiguities, assumptions or   anomalies.

Data  driven solution fails to  produce any outputs  which can be used to communicate your  findings 

Data-driven solution correctly loads the input  data file provided for the  solution. No comments are given on the method used  for their data-driven  

solution. Data-driven  solution can demonstrate  the concept of EDA, as  well as comparisons of the outputs of the appropriate  model outcomes and  metrics but with no  

explanation or comments.  The data-driven solution  showed weak  

demonstration of implicit  knowledge base with some omissions and/or lack of  theory of the use of  

modelling and visualisation for a data project (and  relevant code libraries).  Data-driven solution  correctly uses a package  to produce communication  tools but does not contain  any explanation or  

commentary. 

Data-driven solution correctly loads the input  data file provided for the  solution. Comments are  given on the approach  taken. Data-driven  solution correctly  

handles duplicate values as well as EDA.  

Comments are given.  The solution achieves  the prediction for the  

‘satisfaction’ likelihood  and also correctly  

outputs appropriate  model outcomes and  metrics with reasonable   

level of commentary and explanation. Solution  correctly uses a model  to produce  

communication tools,  with reasonable  

explanations and  

comments. 

Data-driven solution correctly loads the input data file into a Python data structure.  Comments and explanations  are given with detail on the  extract phase of the project.  Data-driven solution handles  duplicate values, missing  values as well as descriptive statistics explaining the steps taken to reach the results.  Notebook also achieves  prediction for the  

‘satisfaction’ Likelihood with  good explanation and  

comments about the method  used. There are model  evaluation metrices  

outputted alongside  

predictions. Solution  

correctly uses a model to  produce communication tools with good explanation and  comments about the method  used.

Data-driven solution correctly loads the input data file provided  for the solution. The comments  provided cover technical details of the extract phase of the project,  demonstrating extensive  

knowledge on generic ETL  process. Solution handles  duplicate values, missing values  and explains in detail the steps  

taken to reach the results.  Correctly uses a model to achieve prediction for the ‘satisfaction’  likelihood and outputs the  appropriate model outcomes and  metrics. Explanations are detailed and profound. Solution correctly  uses a model to produce  

communication tools, with very  detailed explanation and  

comments about the model  output and your chosen method  

of communication conveys this. 

Data-driven solution correctly loads the input data file provided for the  solution in a modular fashion. The  comments provided cover  

exceptional technical details of the  extract phase of the project,  demonstrating extensive knowledge  on ETL processes and their  

peculiarities. Solution handles  duplicate values, handles missing  values, correctly uses a model to  achieve prediction for the future  

trends and outputs the appropriate  model outcomes, metrics as well as  an example of the prediction in action for a new mock entries and  

scenarios. Comments provided are  profound in detail. Explain in detail  the steps taken to reach the results  with further explanation of methods  

to expand the steps taken or process followed. Also explains rationale  behind the methods used. Solution  correctly uses a model to produce  communication tools with very  detailed explanation and comments  about the method used including  examples of similar practices and  suggestions to further enhance the  communication of results. 

Fail 

0-39%

Marginal Fail 40-49%

Pass 

50-59%

Merit 

60-69%

Distinction 

70-79%

High Distinction 80-100% 

30% 

Critically evaluate the use of  models, analysing the  

strengths and weaknesses  (ILO2)

Inadequate and often implicit knowledge  base with some  

omissions and/or lack  of theory relating  to the use of  

programming for  

predictive modelling.  No explanation of loss  function, accuracy  metrics, or  

recommendation of  model for sustaining or increasing  

‘satisfaction’ rate.

Weak and often implicit knowledge base with some omissions and/or lack of  theory relating to the use  of programming for  

predictive modelling. Weak explanation of loss  

function, accuracy metrics, or recommendation of  model for sustaining or  increasing ‘satisfaction’  rate.

Satisfactory knowledge base that  begins to explore and  analyse the theory  relating to the use of  programming for  

predictive modelling.   

Satisfactory explanation  of loss functions,  

accuracy metrices and  comparative strengths of models based on ability  to sustain or increase  ‘satisfaction’ rate  

drawing on the  

academic literature.

Good knowledge base that explores and analyses the  theory relating to the use of  programming for predictive  

modelling. Good explanation  of loss functions, accuracy  metrices and comparative  strengths of models based  on ability to sustain or  increase ‘satisfaction’ rate  drawing on the academic  literature with originality and  autonomy.

Excellent knowledge base that explores and analyses the theory  relating to the use of  

programming for predictive  modelling. Excellent explanation  of loss functions, accuracy  metrices and comparative  strengths of models based on  ability to sustain or increase ‘satisfaction’ rate drawing on the  academic literature with  

considerable originality and  autonomy.

Outstanding knowledge base that explores and analyses the theory  relating to the use of programming  for predictive modelling. Excellent  explanation of loss functions,  accuracy metrices and comparative  strengths of models based on ability  to sustain or increase ‘satisfaction’  rate drawing on the academic  literature with outstanding originality  and autonomy at the cutting edge of  current scholarship.

30% 

Critically using and appraising data visualisation techniques  (ILO3).

Inadequate and often implicit knowledge  base with some  

omissions and/or lack  of theory relating  to the use of EDA,  descriptive statistics  and data visualisation. There are no data  visualisations, neither  in the notebook nor  the report. 

The student did not  explain the justification for performing EDA,  did not present  

appropriate descriptive statistics and has not  explained how EDA  guides model  

selection.

Weak and often implicit knowledge base with some omissions and/or lack of  theory relating to the use  of data visualisation.  There isn’t sufficient  

evidence of useful data  visualisations, neither in  the notebook nor the  report. 

There is weak explanation  for performing EDA,  

coming up with appropriate descriptive statistics and  

how EDA guides model  selection.

Satisfactory knowledge base that  begins to explore and  analyse the theory  relating to the use of  data visualisation. 

The student has  

presented several  

appropriate data  

visualisations,  

communicating insights  visually both in the  report and the notebook. 

There is satisfactory  explanation for  

performing EDA,  

appropriate descriptive  statistics and how EDA  guides model selection.

Good knowledge base that explores and analyses the  theory relating to the use of  data visualisation. 

The student has presented  several appropriate data  visualisations,  

communicating insights  visually both in the report and the notebook. 

There is good explanation for performing EDA, appropriate  descriptive statistics and how EDA guides model selection.

Excellent knowledge base that explores and analyses the theory  relating to the use of data  visualisation techniques.  

The student has presented  several high-quality data  

visualisations, excellently  communicating insights visually  both in the report and the  notebook. 

There is excellent explanation for  

performing EDA, appropriate  descriptive statistics and how  

EDA guides model selection.

Outstanding knowledge base that explores and analyses the theory  relating to the use of data  

visualisation. 

The student has presented several  outstanding data visualisations,  excellently communicating insights  visually both in the report and the  notebook. 

There is outstanding explanation for  performing EDA, appropriate  descriptive statistics and how EDA  guides model selection. 

There are examples of data  

visualisation techniques at the cutting edge of industry using a variety of  methods.

Modelling and Visualisation 

Fail 

0-39%

Marginal Fail 40-49%

Pass 

50-59%

Merit 

60-69%

Distinction 

70-79%

High Distinction 80-100% 

5% 

Academic Research and  Referencing Skills

Inadequate critical analysis or evaluation  with some difficulties.  Largely imitative and  descriptive. Some  

difficulty with structuring  the line of logical  

argument and accuracy  in expression of  

argument.

Limited critical analysis and/or evaluation with  reflection and  

broad evidence-based  critique. Solid structure or  argument including line of  logical reasoning and  accuracy in expression of  argument.  

Satisfactory critical analysis and/or  

evaluation. Good  

reflection and solid, well reasoned judgements  forming from evidence based critique.  

Consistent logical  

structure of argument  including the line of  reasoning and accuracy  in expression of  

argument.  

Good critical analysis and/or evaluation  

skills. Demonstrates intellectu al originality and  

imagination 

Assumptions are clearly  stated.

Excellent critical analysis and/or evaluation  

skills. Demonstrates intellectual  originality,  

integrity, coherence and  

imagination. 

Assumptions are clearly stated.

Outstanding critical analysis and/or evaluation. Demonstrates intellectual originality, integrity,  

coherence, creativity and imagination working consistently in the higher  cognitive domains to a professional  standard. 

Assumptions are clearly stated.

5% 

Follow the guidelines given  in Section 3 Research and  Referencing

Inadequate references and notes but may  contain  

inconsistencies, errors or omissions.

Limited and full and appropriate references and notes with minor or  

insignificant errors 

Satisfactory with precise, full and  

appropriate references  and notes.

Good with precise, full and appropriate references and  notes at a high standard.

Excellent with precise, full and appropriate references and notes  at near-publishing standard.

Outstanding with precise, full and appropriate references and notes at  publishing standard.

Overall Grade 

Overall Grade 

Your submission demonstrates a limited understanding of the  key concepts and  theories covered in the module.  Your analysis  is superficial and lacks critical thinking or  evidence-based  

support.  Your writing  is unclear,  

disorganised, and  contains significant  errors.

Your submission 

demonstrates a limited  understanding of some  (you could include a   

specific number) of the  key concepts and  

theories covered in the  module. You have  

attempted to apply these concepts to the chosen  project or case study,  but your analysis is limited and lacks  

depth. Your writing is  somewhat unclear and  contains some errors.

Your submission 

demonstrates a  

satisfactory  

understanding of the  key concepts and  theories covered in the module. You have  applied these concepts to the chosen project  or case study with  some success. Your  analysis is generally  clear and logical but  may lack depth or  critical thinking. Your  writing is mostly clear  and organised, with  few errors.

Your submission 

demonstrates a good  understanding of the key  concepts and theories  covered in the module.   You have effectively  applied these concepts to  the chosen project or case  

study, providing a well structured and insightful  analysis.  Your writing is  clear, organized, and free  of significant errors.  You  have demonstrated a  strong understanding of  the subject matter. 

Your submission demonstrates an excellent understanding of  the key concepts and theories  covered in the module.  You  have applied these concepts to the chosen project or case  study with exceptional clarity,  depth, and critical thinking.   Your analysis is highly  

insightful and demonstrates a  strong grasp of the  

complexities involved in your  field of study.  Your writing is  exemplary, clear, concise, and  

free of errors.  You have  exceeded expectations and  demonstrated an outstanding  understanding of the subject  matter. 

Your submission demonstrates an exceptional understanding of the  key concepts and theories  covered in the module.  You have  applied these concepts to the  chosen project or case study with  deep insight, originality, and  critical thinking.  Your analysis  demonstrates a deep  

understanding of the innovative  advancements in your field of  study. Your writing is outstanding, setting a new standard for clarity,  conciseness, and originality.  You  have exceeded all expectations  and demonstrated an unparalleled  mastery of the subject matter.