Imaginary Journey to the Frontier of AI: A Glimpse into the Year 2912

In this imaginative journey to the frontier of AI, we’ll project ourselves into the year 2912, where we will challenge the Data Analysis module of ChatGPT v4 to solve a space-time anomaly.

interstellar titanic ship

To break the ice, I asked ChatGPT to briefly describe, based on its knowledge, how it imagines humanity in the year 2912, especially in relation to intergalactic travel.

“By the year 2912, I envision humanity as a highly advanced civilization, spread across multiple planets and star systems. Thanks to discoveries in physics and bioengineering, humans are able to adapt to different space environments and have developed intergalactic travel technology that allows crossing vast cosmic distances in a short time. Spacecrafts are elegant and sophisticated, equipped with AI systems to assist and protect travelers. Human cultures are diverse, influenced by various space colonies, yet united by a common quest for exploration and knowledge.”

I share ChatGPT’s optimism, which doesn’t describe a dystopian future or conflicts, but collaboration among civilizations; probably a reflection of its algorithms’ optimism bias.

Now, let’s describe our intergalactic problem presented on Kaggle:

Addison Howard, Ashley Chow, Ryan Holbrook. (2022). Spaceship Titanic. Kaggle

The interstellar spaceship Titanic, on its maiden voyage, is transporting about 13,000 emigrants from our solar system to three newly habitable exoplanets. Passengers come from Earth, Mars, and Europa, some in cryogenic sleep. The ship offers various services, including VIP treatments, a SPA, a shopping center, and a high-tech Virtual Reality deck. All onboard activities are tracked by a next-generation computer system.

Near Alpha Centauri, en route to the torrid 55 Cancri E, the ship encounters a space-time anomaly hidden by a dust cloud. After 1,000 years, it seems the tragedy of the previous Titanic is repeating in space.

After the impact, although the ship remains miraculously intact, nearly half the passengers are teleported to an alternate dimension!

view of spaceship

To aid rescue teams and recover the missing passengers, we must predict which passengers have been teleported using data from the damaged computer system.

Here’s where we come in with the assistance of ChatGPT v4 and its Data Analytics module.

We face a synthetic problem, created in the lab, which I consider extremely valid and complete to delve into various themes related to data analysis and machine learning algorithms.

To effectively solve these types of problems typically requires complex theoretical and programming knowledge. ChatGPT assists the operator by guiding through all stages of the process.

Here are the details of the Spaceship Titanic problem:

We start with a training file containing data on two-thirds of the passengers and information on whether they have been teleported, and a test file with the same data but no information on the remaining passengers’ teleportation status.

The challenge is to predict, as accurately as possible, whether the passengers in the test file will be teleported.

Here are the known passenger data.

PassengerIdA unique ID for each passenger, in the format gggg_pp where gggg indicates a group the passenger belongs to and pp is the passenger number within the group.
HomePlanetThe planet the passenger departed from, usually their permanent residence planet.
CryoSleepIndicates whether the passenger chose to be put in suspended animation for the journey. Cryosleep passengers are confined to their cabins.
CabinThe cabin number where the passenger is located. Presented in the format deck/number/side, where the side can be P for Port (left) or S for Starboard (right).
DestinationThe planet where the passenger disembarks.
AgeThe passenger’s age.
VIPIndicates whether the passenger paid for a special VIP service during the trip.
RoomServiceAmount the passenger charged to room service. NameThe names and surnames of the passenger.TransportedIndicates whether the passenger has been transported to another dimension. This is the target variable, the column we are trying to predict.

FoodCourtAmount the passenger charged to the food court.
ShoppingMallAmount the passenger charged to the shopping center.
SpaAmount the passenger charged to the spa.
VRDeckVRDeckAmount the passenger charged to the virtual reality deck.
NameThe name and surname of the passenger.
TransportedIndicates whether the passenger has been transported to another dimension. This is the target variable, the column we are trying to predict.
known passenger data

I attempted to solve the problem using ChatGPT v. 4.0 utilizing its Data Analysis module.

After presenting the training file, ChatGPT reprocessed it in the best way and also proposed the best strategies for managing missing data.

Spoiler Alert if you want to tackle this problem without any information.

I asked ChatGPT to explain how these variables might influence the Target Transported variable, and here’s the response:


Predicting whether a passenger has been teleported or not is based on analyzing various factors (or variables) in the dataset. Here’s a brief summary of how some of these variables might influence the probability of being teleported:

HomePlanet (Planet of Origin): The probability of being teleported may vary depending on the passenger’s planet of origin. There could be specific trends or policies associated with each planet influencing this probability.

CryoSleep (Cryogenic Sleep): Passengers in cryogenic sleep may have a higher probability of being teleported, perhaps due to specific procedures or protocols related to their state.

Cabin (Cabin): The type or location of the cabin might correlate with the probability of being teleported, perhaps due to proximity to specific teleportation devices or areas of the spacecraft.

Destination (Destination): The final destination might influence the probability of being teleported, perhaps due to different procedures for different places or travel distances.

Age (Age) and VIP: Though with a weaker correlation, age and VIP status may play a role, potentially due to policies or preferential treatments for certain age groups or VIPs.

Expenses (RoomService, FoodCourt, etc.): Expenditures in various categories (like RoomService, FoodCourt, etc.) show a correlation, suggesting that a passenger’s spending behavior might be linked to their probability of being teleported.

It’s important to note that these are correlations observed in the data and do not necessarily imply a direct cause-effect relationship. Teleportation decisions might be influenced by a complex interplay of these factors and others not captured in the dataset.


The analysis phase was truly impressive, considering it was completely automated.


During the model construction phase, ChatGPT guided us through various stages. Errors occurred several times, which were analyzed and recovered more or less effectively. A major limitation is that more complex computations are also interrupted due to timeout.

ChatGPT suggested using the Random Forest algorithm for the model.

I asked for the rationale behind this choice.


I chose the Random Forest model to predict the teleportation status for various reasons, making it particularly suitable for this type of problem:

Handling Categorical and Continuous Variables: Random Forest effectively manages both categorical and continuous variables. In the provided dataset, we have both types of variables, making Random Forest an appropriate choice.

Robustness to Noisy Data and Outliers: Random Forest is known for its robustness to noisy data and outliers, which can be present in real datasets like this.

Lower Risk of Overfitting: Thanks to its ensemble algorithm nature, combining the results of many decision trees, Random Forest tends to have a lower risk of overfitting compared to single decision trees.

Variable Importance: Random Forest provides useful insights into variable importance, which can help understand which factors most significantly influence the prediction. This is useful for interpreting the model’s results in relation to the business problem.

Good Overall Performance: Generally, Random Forest is known for its good performance across a wide range of classification problems, making it a reliable starting point for many machine learning applications.

Flexibility and Scalability: It’s a flexible model that can be easily adapted to improve performance (e.g., adjusting the number of trees) and scales well with large datasets.

In summary, I chose Random Forest for its robustness, reliability, and ability to provide high-quality results on a complex dataset like the one provided.


The result achieved was an accuracy of 0.79822, which I find astonishing given that it was conducted in a fully guided mode; we also placed reasonably well on the leaderboard for this problem.

These are the parameters obtained on the validation set.

Precision (False)0.8000
Precision (True)0.7800
Recall (False)0.7700
Recall (True)0.8100
F1-Score (False)0.7800
F1-Score (True)0.8000
validation set parameters

All the Python code created can be viewed, which is extremely useful for beginners.

ChatGPT V4 Data Analysis proved to be an incredible assistant, albeit a bit unstable as there were errors that forced me to start over.

All images were created by DALL·E 2 through ChatGPT v4.


Kaggle Competition – Titanic – Machine Learning from Disaster – Predict survival on the Titanic

L’RMS Titanic è stato un transatlantico britannico della classe Olympic naufragato nelle prime ore del tragico 15 aprile 1912, durante il suo viaggio inaugurale, a causa della collisione con un iceberg avvenuta nella notte.

La sfida proposta da Kaggle: Titanic – Machine Learning from Disaster alla quale ho aderito, richiede l’analisi di un dataset contenente informazioni relative ad un sottoinsieme di passeggeri imbarcati sul Titanic con lo scopo di realizzare un modello predittivo che sia in grado di classificare al meglio se un determinato passeggero si salverà dal naufragio.

tassi di sopravvivenza per classe

Alcune delle informazioni disponibili per l’analisi, di cui occorre individuare il livello di correlazione con la probabilità di salvezza, sono: sesso, età, cabina, classe, ponte, numero di parenti a bordo, porto di imbarco, tariffa pagata; moltissime altre informazioni possono essere derivate da elaborazioni più o meno complesse ed implicite tra i dati disponibili come ad esempio dai nomi completi è possibile risalire ai titoli, ad alcune professioni o anche spingersi al raggruppamento delle famiglie.

La grande sfida è quella di spingere al massimo l’accuratezza del modello predittivo al fine di classificare al meglio un insieme di passeggeri di test di cui non è nota la sorte; solo dopo la sottomissione a Kaggle si scoprirà il livello di accuratezza raggiunto.

Il modello predittivo di base che occorre superare e contro il quale ci si deve confrontare, che ho definito come modello baseline, assume semplicemente che tutte le donne si salveranno; applicando questa condizione elementare, si raggiunge un’accuratezza dell’insieme di passeggeri da classificare di poco superiore al 76%.

modello baseline: tutte le donne si salvano raggiunge un’accuratezza dello 0.76555

Questa competizione è un’ottima introduzione alla piattaforma Kaggle e richiede lo sviluppo di tutte le fasi di costruzione di un modello predittivo: analisi dei dati, preparazione e raffinamento dei dati, visualizzazione dei dati, costruzione del modello, validazione del modello e della sua accuratezza, comprensione della piattaforma Kaggle.

Nel mio notebook ho deciso di affrontare la sfida in Python costruendo un modello tramite la libreria XGBoost nota sia per essere alla base delle migliori implementazioni all’avanguardia del settore ma anche perché alla base dei modelli vincenti delle competizioni Kaggle. Tale libreria implementa il framework Gradient Boost in modalità estremamente scalabile, efficiente e portabile.

La mia implementazione, già completamente funzionante, è ancora in evoluzione è raggiungibile a questo indirizzo:

Kaggle Competition – Titanic – Machine Learning from Disaster – Predict survival on the Titanic – Luca Amore


Infection Spread Simulator Construction Kit

Al fine di comprendere meglio l’articolo: Modeling How Infectious Diseases like Coronavirus Spread ed i riferimenti citati, continuando ad approfondire, mi sono ritrovato a costruire il framework: “Infection Spread Simulator Construction Kit”.

Si tratta di un notebook Python su Colab per la modellazione della diffusione di un’infezione attraverso un modello SEIR descritto da un sistema di equazioni differenziali (o un algoritmo); lo stesso modello proposto per l’analisi della diffusione del covid-19 nell’articolo che ha ispirato questo lavoro.

Chiunque, anche senza nessuna base matematica, con una conoscenza basilare di programmazione, può modificare il notebook all’interno della propria sandbox Colab, descrivere un virus o il comportamento di un’infezione ed analizzare la sua diffusione nel tempo per comprendere come la variazione di certi parametri può incidere nella diffusione.

Si tratta di un prototipo, nato per uso strettamente personale, con molti limiti ma voglio comunque condividerlo con la comunità rilasciandolo come software libero sotto la licenza GNU/GPL v.3.

Sarei felice di ricevere i vostri feedback, i vostri modelli, le vostre evoluzioni anche direttamente su github. Nei prossimi giorni, utilizzando questo framework o una sua evoluzione, vorrei provare a realizzare il complesso modello di diffusione del covid-19 descritto nell’articolo.

Segue il link diretto al notebook su github:


Il primo modello reale (non SEIR) che rilascio è quello della malaria. In questo caso ho dovuto apportare delle modifiche più complesse al modello base.