Posts

Machine Learning For Trading: Classification Algorithms for Asset Price Movement

Overview Many people have tried to use machine learning in various implementations in order to forecast trends and trade securities. John Fawcett and Alex Izydorczyk, among others have discussed the topic on the Quantopian community. Here we’ll walk through a comparison of a simple classification strategy and compare results between different classifiers, using Quantopian’s Zipline backtester to help prototype the strategy. Feature Generation For any security (s_k), let vector

More Microbiome Secrets

A new revolution is about to start - get in on the ground floor! Well, it’s been a few months since the last posting on the huge unmet clinical need for microbiome analytics. And the market map still looks roughly the same. The genomic revolution has been happening for 15+ years. Nowadays, genomics is prevalent in almost all major areas of biological science. However, we are still in the early days of the microbiome revolution.

A Secret About Drug Development

People watching pharma companies and the drug development process (this includes investors/VCs, academia and the general public) from the outside will seldom think about this unmet need. The Problem If you’re a scientist, you don’t participate in the upside but you participate a lot in the downside in the case a drug fails to make it past trials and onto the market.. This isn’t exactly a secret (see interview: Vivek Ramaswamy, Roivant Sciences CEO), but is something casual biology enthusiasts or scientists in academia may not appreciate.

A Secret About Drug Development

People watching pharma companies and the drug development process (this includes investors/VCs, academia and the general public) from the outside will seldom think about this unmet need. The Problem If you’re a scientist, you don’t participate in the upside but you participate a lot in the downside in the case a drug fails to make it past trials and onto the market.. This isn’t exactly a secret (see interview: Vivek Ramaswamy, Roivant Sciences CEO), but is something casual biology enthusiasts or scientists in academia may not appreciate.

Short Roku

Roku (NASDAQ: ROKU) Date written: Feb 15, 2018 Current price: $45 Price target: $20-25 (45-55% gain) Time frame: 6-12 months Recommendation What: SHORT with price target of $20/share (50% to gain). Time frame: 6-18 months. Why: Overly ambitious user growth estimates Inferior hardware product Limited potential for company to cut costs Catalysts: Potential earnings miss (2/21/18) Missed earnings will cause a sell-off IPO lockup period ends March 2018 => stock price will drop Series B converted shares will get sold off => stock price will drop Risks:

Speech Analysis

Unmet needs in areas requiring machine learning Stroke The number 1 loss of ability to speech in adults is stroke. A stroke happens roughly every 45 seconds across all people in the world. A stroke is a focal lesion, which can hit in any area of the brain. When it hits Broca’s area (responsible for speech production) or Wernicke’s area (responsible for speech formulation), speech is impaired. Autism A major shortfall of speech language therapists is in assessing and helping patents with autism.

Bottos (BTO): the best AI crypto of 2018

A large problem with artificial intelligence today lies in the lack of reliable data sources. To be successful, many companies have had to rely on having exclusive access to data. This works fine for large companies with clout like Google and Facebook, but puts small and medium size businesses at a huge disadvantage. Bottos is solving this problem with a blockchain solution for data sharing as well as AI model sharing.

Behavioral imaging is the future of medicine

Human behavior can be: 1. measured using sensors 2. quantified using states 3. analyzed using machine learning In the past, behavior has been quantified in primitive ways. Despite lack of quantification, many diseases progress due to behavioral factors. Cancer costs $$ for the health care system, but many health outcomes are driven by behavior. * Stress costs $190B/yr * Smoking cost $326B/yr [leading cause of premature death] * Substance abuse costs $100B+/yr These things aren’t just expensive, but there is generally a HUGE desire in people that smoke, abuse drugs, etc to change their behavior.

A secret on microbiome startups

In the first year of medical school (2012), a professor told us about fecal transplants. The entire class laughed, simultaneously dismissing the idea and making inappropriate jokes. Fast forward a few years, fecal transplants are being performed more, and patients’ microbiomes are being sequenced. Research has linked the human gut microbiome to diseases such as systemic lupus erythematosis (clinical trial). The interest in the microbiome is exploding. Meanwhile, genomics interest has decreased rapidly since the GWAS bubble, and stayed relatively constant.

Still long on Gilead (GILD): $120 PT

Price target: $120 Time frame: 1-2 years A year after my original call (http://https://rchenmit.github.io/2016/08/13/gilead-one-mans-sickness-is-another-mans-profit/), I am still long GILD. The positive drivers clearly outweigh the overblown fears. Positive Drivers: the recent Kite Pharma acquisition Gilead will continue to print money with non-alcoholic steatohepatitis (NASH) drugs Overblown Fears: “the hepatitis C (HCV) revenues are decreasing!” “the HCV patents are expiring!” The overblown fears should be non-issues.