Experienced scientist with over five years of experience in large-scale big data research with a keen eye for aesthetic excellence in communicating results intuitively to stakeholders. Eager to transfer scientific rigor, relentless work-ethic, and excellent team working skills into powerful data science that offers actionable insights to inform and guide successful managerial decision-making.
My Academic Contributions
Hennig-Thurau, T., Aliman, D.N., Herting, A.M., Cziehso, G., Linder, M. & Kübler, R. (2023) Social interactions in the metaverse: Framework, initial evidence, and research roadmap. Journal of the Academy of Marketing Science 51, 889–913.[link]
Linder, M., Behrens, M. & Hennig-Thurau, T. (2023) Telling Great Stories with Ads: Determining the Drivers of Narrative Advertising Effectiveness. Proceedings of 2023 AMA Winter Academic Conference 34, 240-242
[link]
*Kupfer, A.-K., Pähler vor der Holte, N., Kübler, R. & Hennig-Thurau, T. (2018) The Role of the Partner Brand's Social Media Power in Brand Alliances- Journal of Marketing 82, 25-44.
[link]
*In supporting role as coder.
Given by my career in academic research, my daily activities involed advanced statistical analysis in R. While I cannot share these projects publically, here's a compilation of Python data science projects I've undertaken for educational purposes. While I used multiple packages within each, I highlighted some packages, whose power the project highlights. Feel free to click on the project name to explore the details of each project.
| ID | Project Name / Dataset | Data Science Concepts Showcased | Package in Focus | Module | Function(s) |
|---|---|---|---|---|---|
| 1 | US Medical Insurance Cost | Exploratory Data Analysis (EDA) | numpy, pandas | misc. | |
| 2 | Life Expectancy & GDP | Data Visualization | matplotlib, seaborn | misc. | |
| 3 | Stock Price Prediction | Linear Regression | sklearn | .linear_model | LinearRegression() |
| 4 | Census Income (LogReg) | Logistic Regression | sklearn | .linear_model | LogisticRegression() |
| 5 | Breast Cancer | K-Nearest Neighbors (KNN) Classification | sklearn | .neighbors | KNeighborsClassifier() |
| 7 | Flags | Decision Trees (incl. pruning) | sklearn | .tree | DecisionTreeClassifier() |
| 8 | Obesity | Wrapper Methods | mlxtend | .feature_selection | SequentialFeatureSelector() [SFS, SBS], RFE() |
| 9 | Wine Qualiy | Regularization | sklearn | .linear_model | LogisticRegressionCV() |
| 10 | Raisins | Hyperparameter Tuning | sklearn | .model_selection | GridSearchCV(), RandomizedSearchCV() |
| 11 | Particles | Principial Component Analysis | sklearn | .decomposition | PCA() |
| 12 | Census Income (RanFor) | Random Forest Classification | sklearn | .ensemble | RandomForestClassifier(), BaggingClassifier(), RandomForestRegressor() |
| 13 | Census Income (Boosting) | Boosting | sklearn | .ensemble | AdaBoostClassifier(), GradientBoostingClassifier() |
| 14 | Book Recommender | Recommender System | surprise | KNNBasic() | |
| 15 | Strike Zone | Support Vector Machines | sklearn | .svm | SVC() |
| 16 | Email Similarity | Naive Bayes Classification | sklearn | .naive_bayes | MultinomialNB() |
| 17 | Logic Gates | Perceptrons | sklearn | .linear_model | Perceptron() |
Here's also a compilation of Python deep learning projects I've undertaken for educational purposes. Current focus lies on exploring tensorflow/keras and pytorch at depth. Feel free to click on the project name to explore the details of each project.
| ID | Project Name | Deep Learning Concepts Showcased | Package in Focus | Module | Function(s) |
|---|---|---|---|---|---|
| 1 | Predicting Graduate Admission | Simple Regression/Prediction using Deep Learning | tensorflow | .keras | KerasRegressor / output activation = 'linear' |
| 2 | Predicting Life Expectancy | Simple Regression/Prediction using Deep Learning | tensorflow | .keras | KerasRegressor / output activation = 'linear' |
| 3 | Predicting Heart Failure | Simple Classification using Deep Learning | tensorflow | .keras | KerasClassifier / output activation = 'softmax' |
| 4 | Neural Machine Translation (NMT) | Long short-term memory networks (LSTMs) | tensorflow | .keras | LSTM() |
| 5 | Classifying Galaxy Images | Convolutional Neural Networks | tensorflow | .keras | Conv2D(), MaxPooling() |
| 6 | Classifying X-rays | Convolutional Neural Networks / Computer Vision | tensorflow | .keras | Conv2D(), MaxPooling() |
| 7 | Classifiying Cat Images | Transfer Learning with pre-trained neural networks | (py)torch | nn.Linear() | |
| 8 | Multi-Layer Perceptron | MLP: modern feedforward fully connected artificial NN | (py)torch | self defined class Net(nn.Module) | |
| 9 | Image Classification, CIFAR10 | Math of dimension transformation within CNN | (py)torch | Conv2d(), relu(), pool(), dropout(), Linear() | |
| 10 | Sentiment Analysis Movie Reviews | Sentiment Analysis with Recurrent Neural Networks | (py)torch | misc. |
Here's also a compilation of Python natural language projects I've undertaken for educational purposes. Feel free to click on the project name to explore the details of each project.
| ID | Project Name | NLP Facet Showcased | Package in Focus | Module | Function(s) |
|---|---|---|---|---|---|
| 1 | Classical Texts | Language Parsing | nltk | RegexpParser() | |
| 2 | Mystery Friend | Bag-of-Words Language Quantification | sklearn | .feature_extraction.text | CountVectorizer() |
| 3 | News Content | Term Frequency-Inverse Document Frequency (tf-idf) | sklearn | .feature_extraction.text | TfidfTransformer(), TfidfVectorizer() |
| 4 | Presidential Vocabulary | Topic Modelling (Word Embeddings) | gensim | .models | Word2Vec() |
| 5 | Multi-Topic Chatbot | Rule-based chatbot using regex | re | match() | |
| 6 | Denver Broncos Restaurant Chatbot | Retrieval-based chatbot using topic modelling | misc. | misc. | TfidfTransformer(), Word2Vec() |
| 7 | Generative Chatbot | Generative chatbot using topic modelling | misc. | misc. | TfidfTransformer(), Word2Vec() |
In addition, I am currently working on extending my knowledge on machine learning engineering. Feel free to click on the project name to explore the details of each project.
| ID | Project Name | ML Facet Showcased | Package in Focus | Module | Function(s) |
|---|---|---|---|---|---|
| 1 | Hierarchical Classes | Hierarchical Classes, Object-Orienter Programming | - | - | __ init __, __ repr __, .methods() |
| 2 | ATM Logging | Logging | logging | Stream/FileHandler, etc. | logger() |
| 3 | Surf Shop | Unit Testing | - | unittest | self.assertRaises, self.subTest(), self.assert.. |
| 4 | Concurrent Programming | Sequential, Async, Threading & Multiprocessing Progamming | - | threading, asnycio, multiprocessing | Thread(), Process() |
| 5 | Bone Marrow Disease Classification | Machine Learning Pipelines | sklearn | pipeline | Pipeline(), ColumnTransformer() |
Beyond coding for educatioanl purposes, I do enjoy coding for fun in my free time. Here's a compilation of projects I've undertaken with various objectives. Again, feel free to click on the project name to explore the details of each project.
| ID | Project Name | Objective | Language | Package in Focus | Function(s) |
|---|---|---|---|---|---|
| 1 | Hierarchical Bayesian multinomial logit analysis | Create lighthouse/sawtooth report content and structure of hierarchical Bayes logistic regression analysis | R | ChoiceModelR | |
| 2 | NFL Stats | Scrape NFL stats from the official website for the 2023 season, covering multiple categories | Python | .bs4 | BeautifulSoup() |
Here's a selection (in alphabetic order) of the packages/platforms/libraries I have worked with over the years:
PinnedLoading
- hb_lighthouse_report_in_R
hb_lighthouse_report_in_R PublicThis R-code will show you how to recreate the typical lighthouse/sawtooth report content and structure of a hierarchical Bayes logistic regression analysis using data collected with choice-based co…
R 2
If the problem persists, check theGitHub status page orcontact support.