References: Wu, SH., Chen, YC., Chen, CH. et al. (2024). Caffeine supplementation improves the cognitive abilities and shooting performance of elite e-sports players: a crossover trial. Sci Rep 14, 2074 https://doi.org/10.1038/s41598-024-52599-y

A recent study published in Knowledge and Information Systems shows us an analysis of machine learning (ML) models for predicting the future performance of  basketball players. This study tested 14 different ML models against 18 basketball statistics and Key Performance Indicators (KPIs).

Methodology and Data Focus

The researchers applied their methodology to a pool of 90 NBA players. To qualify, players had to meet strict criteria based on high averages across crucial KPIs like GameScore (GMSC), FOUR FACTORS, TENDEX, Fantasy Points (FP), and Efficiency (EFF) and the players had to have had a good amount of participation time (15+ minutes) over three recent seasons  (2019–20 up to 2021–22).

The study focused on developing individual scenarios for each player and the players averages in their past games in order to predict upcoming games. The 14 ML models tested spanned several categories, including Linear-Based models, Tree-based models, Non-Parametric (K-nearest neighbors or KNN), and Online-Learning models. To keep it simple, the study used different versions of models that best suit the measuring category.

In order to rank the models in comparison to each other, the authors made an evaluation metric called the weighted average percentage error (WAPE), which is derived from the weighted Mean Absolute Percentage Error (MAPE) results for each statistic and model.

Key Findings: Tree-Based Models Dominate

The research clearly showed that the Tree-based models are the best performers across most of the tested performance indicators.

The best models, based on performance against unseen data, were ranked as follows by WAPE score:

1. Extra Trees (ET): Achieved the best performance with a WAPE of 34.14%. ET was a better predictor for metrics such as AST RATIO, PIE, PM, and TOV.
2. Random Forest (RF): Scored a WAPE of 34.23%.
3. Decision Tree (DT): Scored a WAPE of 34.41%.

While Tree-based models were really good, certain Linear-Based models like LASSO (34.54% WAPE) and LARS (34.53% WAPE) also showed exceptional overall performance, demonstrating good accuracy for specific metrics.

Optimizing KPI Forecasting

A crucial finding of the study was the success of a comprehensive forecasting approach designed to improve KPI prediction results, specifically focusing on Fantasy Points (FP).

Instead of forecasting FP as a single combined metric, the researchers experimented with forecasting the six constituent individual metrics (Points, Rebounds, Assists, Steals, Blocks, and Turnovers) separately, and then constructing the FP KPI from these predictions.

This optimized approach led to a significant improvement. The overall forecasting accuracy for FP improved by 3.6% MAPE on unseen data when utilizing this method. The Gradient Boosting Machine (GBM) model, for instance, achieved a MAPE of 29.81% when using the reformatted approach, which outperformed the best result from the single-metric forecast approach (LARS at 33.39% MAPE).

Implications

The findings show us lots of new  insights for the sports analytics industry, including researchers, coaches, data scientists, and organizations that invest in creating data science departments for scouting insights. The research not only benchmarks current ML model performance but also introduces an innovative approach to improve KPI forecasting accuracy, showing us that advanced statistical techniques combined with practical methods can set a new benchmark for predicting professional basketball player performance. Future work suggested by the authors includes incorporating external factors such as sentiment analysis, betting odds, and motion capture data to further refine predictions.

What does this mean for the future of sports? 

We are heading towards a future where statistical analysis can help teams attract the best talent and retain the best evaluate performers. The benchmarks are only getting better and more accurate. This begs the question of whether this is fair or not? Would it be fair for a team to cut a players contract based on data from a machine learning model? As these models start becoming more and more involved in team environments, the ethical considerations of using these models are going to start taking effect as well. So, what do you think; do you think these models are doing more good than bad for sports?

 

Reference

My Challenges with AI

AI has taken over the world of technology; from software developers to artists, AI has an effect on almost all of us these days. In this essay I will be talking about the effects AI had on me as a college student and weigh out the good, the bad and the ugly.

The Good

Starting off with the good. AI has immensely aided in my understanding of various subjects from Computer Architecture (CS 2200) to understanding the Psychology of Cybersecurity (CS 4263). Whenever I am stuck, I see AI as an instant solution towards understanding the topic that I am having trouble with. Instead of having to wait for answers of Piazza or Ed discussion, or wait in lines at office hours, I am able to head over to an AI chatbot and get my answers instantly. Now you may be wondering, what if the answers are wrong? Well to limit this I give the AI the correct context. For example, if I am studying for a quiz for a math course, I would give the AI the correct lecture slides, textbook, study guide, etc. and then ask it questions based on the material. This strategy is especially useful with LLMs such as Notebook LM because it will only give you answers based on the text that you give it and no outside sources (unless you prompt it to use outside sources). AI also gives me the ability to really dig deep into a topic by asking it questions until I get a thorough understanding. This is especially beneficial in classes where office hours are usually crowded and you are not able to have too much time with the TA. The AI can serve as your substitute TA.

The Bad

Now, although these use cases help in bettering my education, there are many use cases where AI has done the opposite. The rise of AI in the past 3 years has caused many professors to begin to integrate it within courses. The professors understand the inevitability of AI usage by students in these courses, so they arrange for it to be available to students, but with various restrictions. One of the most common restrictions is copy and paste. Copying and pasting content from an LLM to an IDE or to wherever your workspace is, is almost always a violation in many courses. Having this type of tool freely available to students is very dangerous when it comes to our education. It is very easy and tempting for students to simply finish the assignment using AI. It is like having all the answers to the test, but you force yourself to not take a lot before going into the test. Although the restrictions help, they only do so much in restricting AI usage. In my personal experience, AI usage has done more good than harm for my education, but there are definitely instances (especially in essay writing) where I used AI to accelerate my writing process.

The Ugly

That was the bad part of AI, now let’s get into the ugly. The ugly part of AI usage is essentially a more extreme use of what I stated in the bad. AI use in the wrong students’ hands can be extremely detrimental to their education. From my personal experience as a student I can completely see how someone can get through all 4 years in college without learning a thing and simply just using AI. Especially with the larger tokenized models that continue to release every few months, I speculate that in less than a year (unless colleges find extreme AI detection resources) there are going to be many students that can achieve their whole degree with just AI.

To sum up my position through my anecdotal experience, I would say that the benefits of and detriments of AI all depend on the person using it. If someone wants to better their education by using AI as a partner to learn then they would benefit tremendously, but if one simply uses AI as a tool to complete all of their assignments then they would reap the detriments of AI usage.

 

Introduction

Recently, I found myself unable to do nothing, even for a few minutes. It’s like my body itches to be occupied. I think it feels uncomfortable to do nothing, which feels weird to admit. We live in a digital age where we have access to all kinds of information at our fingertips in a matter of seconds, probably more now than ever before. Things feel fast-paced, and we’re already moving on to the next big thing. After some introspection, I thought that it’s been a while since I’ve intentionally felt bored—whenever I’m bored, it’s so easy to find something for me to do. I ran into this video on YouTube, and it got me thinking, “Maybe I really should be bored sometimes!” I ended up doing my Final Speech for my public-speaking class on boredom. It’s time to be bored!

Benefits of Boredom

Boredom comes with several benefits! Here, I’ll discuss some of my favorite reasons to be bored.

Boredom often signals when a situation isn’t working for us. Think of it like a redirection. Our urge to fight boredom can lead to positive change (An et al., 2023b). An example is when we’re doing something boring to us, say, sitting in a meeting that we don’t want to be in. As our mind wanders, we start thinking of better things we could be doing instead, or how we could better manage our time. As a result, another benefit of boredom is increased creativity (Mann & Cadman, 2014). This increase in creativity is often linked to daydreaming, which occurs when bored individuals cannot physically escape their situation, and their attention shifts from external to internal focus on their inner thoughts and feelings (Mann & Cadman, 2014). In Mann and Cadmen’s study, participants who completed a boring, mundane activity performed better on creative challenges than those who didn’t. Boredom facilitates exploration and opportunity because, using our desire for change, we explore alternate goals or information in our environment that we may have missed otherwise (Bench and Lench, 2013). 

Boredom also serves as an opportunity for our minds to rest and reset. When we’re not actively doing anything, our brains can disengage. This causes the default mode network in our brain to kick in, prompting reflection and introspection, which helps us understand ourselves and the world around us (UniSC Youth Mental Health Researcher,  M. K. and P. of Y. M. H. & N. 2025). Boredom also “rebalances the nervous system and reduces sensory input to help calm anxiety” (UniSC Youth Mental Health Researcher,  M. K. and P. of Y. M. H. & N. 2025). You might feel anxious or restless from boredom, so we reach for something for the quick dopamine hit, but it has been found that constant stimulation, especially for our nervous system, can result in increased anxiety; this is because, our sympathetic nervous system regulates our fight-or-flight response, so keeping it on overdrive results in more anxiety (UniSC Youth Mental Health Researcher,  M. K. and P. of Y. M. H. & N. 2025). Simply, we’re better off embracing the boredom from time to time to allow our sympathetic nervous system to reset and recuperate.  

Ways You Can Be Bored

Say on your next walk to somewhere, e.g., class, put your phone away and take in your surroundings. Try doing this without any music, too! After completing a task, take 30 seconds to a minute to do absolutely nothing. Seriously! Turn your brain off just for a minute (or however long you like). It might feel weird in the moment, but I promise, it will be so refreshing and worth it! Try doing everyday tasks without external stimuli, such as no music in the shower or screens when eating. Or, take the mindfulness route by taking a few minutes at the end of each day to think of three things you’re grateful for. These are my recommendations, so I strongly encourage you to find practices that work best for you. The point is to remove external stimulus and to be present in the moment.

Conclusion

Now that you’ve read about the benefits and the ways to be bored, I must clarify that it’s not bad to alleviate your boredom. It’s not bad to want to be productive or reach for something when you feel bored. Know that choosing to be bored sometimes is part of intentional, healthy living. You are worthy of a break. Choosing boredom is choosing you!

Check out Robert Greene’s and Veritasium’s video on boredom, too!

Sources

An, J., Payne, L. L., Lee, M., & Janke, M. C. (2023b). Understanding boredom and leisure in later life: A systematic review. Innovation in Aging, 7(8). https://doi.org/10.1093/geroni/igad109 

Bench, S., & Lench, H. (2013). On the function of boredom. Behavioral Sciences, 3(3), 459–472. https://doi.org/10.3390/bs3030459 

Mann, S., & Cadman, R. (2014). Does being bored make us more creative? Creativity Research Journal, 26(2), 165–173. https://doi.org/10.1080/10400419.2014.901073 .

UniSC Youth Mental Health Researcher, M. K. and P. of Y. M. H. & N. (2025). Boredom gets a bad rap. But science says it can actually be good for us. UniSC. https://www.usc.edu.au/about/unisc-news/news-archive/2025/may/boredom-gets-a-bad-rap-but-science-says-it-can-actually-be-good-for-us

Unironically, beavers are genuinely one of my favorite animals! With their chunky bodies, fluffy fur, five-toed webbed hind feet, five-finger hands, orange bucked teeth, and paddle-shaped tail, what’s not to love about them? They’re so cute! I recently watched Zootopia 2 in theaters, and there was a beaver character named Nibbles! I was THRILLED to say the least! I’ve never seen one in real life, so it’s on my bucket list to meet one someday. 

Here’s a picture of my beaver squishmallows and bidoof plush! The beavers even have a paddle tail if you look closely. Bidoof is a Pokémon inspired by the beaver, and it evolves into Bibarel!

Intro to Beavers

Beavers are large, semi-aquatic rodents of the Northern Hemisphere (Brazier et al., 2020). There are two existing Beaver species: the North American beaver (Castor canadensis) and the Eurasian beaver (Castor fiber) (Brazier et al., 2020). We’re able to tell the difference between the two species based on the number of chromosome pairs: the Eurasian beaver has 48 pairs while the North American beaver has 40 pairs (Lavrov, 1983). Their distinctive features, such as the flat, paddle tail, webbed hind feet, constantly growing teeth, and dense fur, allow them to perform specialized behaviors: damming and tree felling that can transform landscapes, habitat, and water management (Brazier et al., 2020). Beavers use their construction ability to protect themselves from predators; they use their teeth to collect branches and trees to build their dams (“Beavers work to improve habitat”). 

Beavers as Ecosystem Engineers

Beavers are considered ecosystem engineers because their construction capabilities can alter, maintain, or create habitats by redistributing biotic and abiotic resources for themselves and other species (Rosell et al., 2005). There are three main types of lodge structures that beavers can build, and they select their lodge location based on water depth and bank characteristics (Rosell and Campbell, 2022). These lodges are where beavers take shelter, and beavers create underwater entrances to get to the dry living space, often called the chamber, which is where they rest, raise their young, and stay safe from predators (Rosell and Campbell, 2022). The three types are island lodge, bank lodge, and stick lodge (Rosell and Campbell, 2022). The island lodge is more commonly found in North America, and beavers build this type of lodge when the bank is low (Rosell and Campbell, 2022). Because the bank is low, beavers can’t dig a burrow into a bank, so they build upwards (Rosell and Campbell, 2022). “Bank lodges are found on the water’s edge and built around a burrow dug into the bank” (Rosell and Campbell, 2022). Finally, stick lodges are built from material extending from the shoreline (Rosell and Campbell, 2022). To create a more efficient access to food and building resources, beavers dig shallow channels, canals, which extend from beaver ponds (Brazier et al., 2020). Beavers build dams to raise the water level: ”habitats with deep, slow-flowing water keep them safe from predators” (Brazier et al., 2020). There are two types of dams that beavers may build: the primary and secondary dams (Brazier et al., 2020). The primary dam maintains the main lodge pond, which is much larger than the secondary dams; the secondary dams improve mobility and serve to move woody materials (Brazier et al., 2020). 

Beavers are keystone species (Brazier et al., 2020). They literally change their habitat with their engineering instincts for their survival and needs, thus directly changing their habitat’s ecology. If you like to learn more about beavers in a more entertaining format, I highly recommend checking out Lindsay Nikole’s video about beavers! She’s one of my favorite animal content creators!

Sources:

Brazier, R. E., Puttock, A., Graham, H. A., Auster, R. E., Davies, K. H., & Brown, C. M. (2020). Beaver: Nature’s ecosystem engineers. WIREs Water, 8(1). https://doi.org/10.1002/wat2.1494

Beavers work to improve habitat: U.S. Fish & Wildlife Service. FWS.gov. (2025, December 1). https://www.fws.gov/story/beavers-work-improve-habitat

Lavrov, L. S. (1983). Evolutionary development of the genus Castor and taxonomy of the contemporary beavers of Eurasia. Acta Zoologica Fennica, 174, 87-90.

Rosell, F., Bozsér, O., Collen, P., & Parker, H. (2005). Ecological impact of beavers castor fiber and castor canadensis and their ability to modify ecosystems. Mammal Review, 35(3–4), 248–276. https://doi.org/10.1111/j.1365-2907.2005.00067.x

Rosell, F., & Campbell-Palmer, R. (2022). Beavers: ecology, behaviour, conservation, and management. Oxford University Press.

“Fish are friends, not food.” – Bruce from Finding Nemo. When I watched Disney’s Finding Nemo (2003) as a child, I was absolutely horrified by Bruce the Great White Shark. I was so afraid that when I went on family vacations to the beach, I would be wary of sharks patrolling. I would watch out for the triangular fin and didn’t want to stray too far away from the shore. Ironically, I’ve never seen the iconic Jaws (1975) movie. The director, Steven Spielberg, has said he “truly regrets” his portrayal of great white sharks and the movie’s contribution to the animal’s population decline. Even the author of the 1974 book Jaws, which inspired Spielberg’s movie, Peter Benchley, has apologized for the impact his book had on sharks and dedicated the rest of his life to shark conservation! Check out Benchley’s website–it’s awesome!

I’m not sure when I became a big fan of sharks, but I think it might’ve been because I watched a YouTube or TikTok video about them, and since then, I love sharks!

Background

Sharks belong to the class Chondrichthyes, or cartilaginous fish, meaning their skeletons are made of cartilage, rather than bone like other fish (Chapman, 2017). Fossil records have shown that members of this class have been around since 400-450 million years ago, which also means that sharks are older than trees and some dinosaurs (Chapman, 2017)! Chondrichthyans represent “one of the most species-rich lineages of predators on Earth and they continue to play important functional roles in coastal and oceanic ecosystem structure and function” (Chapman, 2017). The Chondrichthyes class has two groups: Holocephali and Elasmobranchii (“Shark Species”). The Elasmobranchii group has 8 orders of sharks, so each order classifies the “biology, physical characteristics, and behavior of sharks in that order” (“Shark Species”). Check out the Shark Research Institute’s website to learn more about sharks from different orders (you can also click on a shark to learn more about them). 

Sharks are typically found in marine habitats (although bull sharks, Carcharhinus leucas, may be found in estuaries and rivers in tropical/warm temperate regions), from shallow coastal waters and the continental shelf and slope to the deep ocean (Bennet, 2005). Sharks are highly diverse, with species ranging in size from about 20cm to over 18m (Dedman et al., 2024).

Here are some fun facts! Whale sharks are the largest fish in the sea—they can grow more than 12m long and can weigh over 21 tonnes (Chapman, 2017). You can visit Yushan, the whale shark, at the Georgia Aquarium (the only US aquarium with a whale shark). I visited the aquarium two summers ago, and whale sharks are really just gentle giants. Greenland sharks are the “longest-lived vertebrate known, with recent studies estimating a lifespan of about 390 years, give or take 120 years” (Nielson et al. 2016). Isn’t it crazy to think a species of shark could outlive three human family generations? 

Ecological Roles of Sharks

It’s actually a misconception that all sharks are apex predators (Chapman, 2017). Their exact role in the ecosystem depends on the “species, region, age/size, behavior, and/or sex” (Chapman, 2017). Chapman explains that apex predators must occupy the highest trophic level, control the ecosystem from the top down, and influence the productivity of the entire system (2015). In addition, “macropredatory and large mesopredatory sharks often induce behavioral shifts in their potential prey through predation risk and possibly competitive interactions with other predators” (Dedman et al., 2024). This means that sharks can impact how prey feed, hide, or move. Most sharks do not uphold these behaviors and would be classified as mesopredators (mid-level predators); only a select few sharks are considered apex predators, i.e., “great sharks” (Chapman, 2017). Sharks are not simply large predators: they can fill ecological roles at varying trophic levels (Dedman et al., 2024). Their diets range from filter feeding (like whale sharks) to parasites to small crustaceans to classic big predators that eat fish, turtles, seals, and other sharks (Dedman et al., 2024). However, it is challenging to create a comprehensive “understanding of ecological roles and the importance of sharks because of the inherent difficulties of studying their interactions and the mechanisms through which sharks may–or may not–affect ecosystems” (Dedman et al., 2024).

Sharks also have a bottom-up and/or facilitation role in ecosystems. Though research here is currently limited, we know that sharks move nutrients across great distances: “from pelagic environments to coral reefs, shallow to deep mesophotic coral reefs and vice versa, coastal oceans to estuarine waters, and across latitudinal gradients” (Dedman et al., 2024). These nutrients are deposited via “egestion and excretion or carcasses of sharks that die” (Dedman et al., 2024). It is worth noting that the ecological importance of this deposition needs to be further studied, as it remains unknown. 

Threats to Sharks

According to Dulvy et al.,”24% of shark, skate, and ray species are considered Threatened with extinction by the IUCN Red List’s Shark Specialist Group (2014). Targeted overfishing and bycatch (unintentional catches) contribute to the shark population decline (Shiffman and Hammerschlag, 2016). Shark fishing involves the sale of meat (for consumption), jaws (as tourist trinkets), cartilage and liver oil (as alternative medicine); the major reason for shark fishing is for shark fin soup (Shiffman and Hammerschlag, 2016). According to the Fisheries and Aquaculture Department (FAO), trade in shark parts is worth approximately US $1 billion annually worldwide (2010). Unfortunately, because of sharks’ slow growth, late maturity, and low reproductive rate, sharks are especially vulnerable to overfishing (Friedrich et al., 2014).

Conservation Efforts 

Raising awareness about shark issues and the destructive impacts human activities have on shark populations has been found to improve attitudes towards shark conservation (Friedrich et al., 2014). At a consumer level, we can consider purchasing sustainably sourced seafood or engage with campaigning for policy change (Friedrich et al., 2014). The image of sharks as fearsome predators greatly limits public engagement and support for shark conservation, which is due to cultural representations in media, such as Jaws and sensationalized media reports of shark attacks (Friedrich et al., 2014). Effective shark protection is rooted in “international strategy, changes to fisheries regulations, and tailored conservation tools (Friedrich et al., 2014). To determine effective conservation strategies, we must study ecological communities, species’ roles, and “the context of pervasive human presence in the oceans” (Dedman et al., 2024). 

Video of Yushan and Taroko from 2024 that I took! Unfortunately, Taroko died in August 2025.

Whale Sharks – Yushan and Taroko at the Georgia Aquarium’s Ocean Voyager

Sources:

Chapman, B. (2017). Shark attacks: Myths, misunderstandings and human fear. Csiro Publishing.

Bennett, M. (2005). The role of sharks in the ecosystem. St. Lucia: School of Biomedical Sciences, The University Of Queensland.

Dedman, S., Moxley, J. H., Papastamatiou, Y. P., Braccini, M., Caselle, J. E., Chapman, D. D., Cinner, J. E., Dillon, E. M., Dulvy, N. K., Dunn, R. E., Espinoza, M., Harborne, A. R., Harvey, E. S., Heupel, M. R., Huveneers, C., Graham, N. A., Ketchum, J. T., Klinard, N. V., Kock, A. A., … Heithaus, M. R. (2024). Ecological roles and importance of sharks in the Anthropocene Ocean. Science, 385(6708). https://doi.org/10.1126/science.adl2362

Dulvy, N.K., Fowler, S.L., Musick, J.A., Cavanaugh, R.D., Kyne, P.M., Harrison, L.R., Carlson, J.K., Davidson, L.N.K., Fordham, S.V., Francis, M.P., Pollock, C.M., Simpfendorfer, C.A., Burgess, G.H., Carpenter, K.E., Compagno, L.J.V., Ebert, D.A., Gibson, C., Heupel, M.R., Livingstone, S.R., Sanciangco, J.C., Stevens, J.D., Valenti, S. & White, W.T. (2014). Extinction Risk and Conservation of the world’s sharks and rays. eLife 3. (Online DOI: doi: 10.7554/eLife.00590).

FAO Fisheries and Aquaculture Department (2010). The state of world fisheries and aquaculture. Rome: Food and agriculture organization of the United States.

Friedrich, L. A., Jefferson, R., & Glegg, G. (2014). Public perceptions of sharks: Gathering support for shark conservation. Marine Policy, 47, 1–7. https://doi.org/10.1016/j.marpol.2014.02.003

Shiffman, D. S., & Hammerschlag, N. (2016). Shark conservation and management policy: A review and Primer for non‐specialists. Animal Conservation, 19(5), 401–412. https://doi.org/10.1111/acv.12265