Platform Research¶

Kavout takes in vast and diverse datasets including fundamentals, pricing, technical indicators, and alternative data, and then uses a combination of statistical analysis and ML techniques with ranking algorithms to deliver an actionable equity rating score with values ranging from 1-to-9.

Value, Quality, Growth, Momentum, Profitability, Volatility, Size and more.

Technical indicators and scores such as MACD, RSI, Z-Score, M-Score and more.

Price patterns such as chart and candlestick patterns.

Time series of the features above as well as price-related data.

Sentiment information such as insider and options trading activities, and text analytics.

2

logo black text predicted the expected return for every asset in a portfolio

We designed an intelligent asset allocation system that utilized Deep Learning and Modern Portfolio Theory. Incorporating Long Short-Term Memory Units to better predict asset returns based on historical data (Long Short-term Memory Recurrent Neural Network (LSTM)). Using a novel technique called Variational Dropout, Another neural network was used to determine the optimal set of weights for the portfolio’s assets.

In order to strengthen our predictions, we used a wealth of market data, such as currencies, indices, etc. in our model, in addition to the historical returns of relevant assets. This resulted in over 400 features we used to make final predictions. Of course, many of these features were correlated. This problem was mitigated by Principal Component Analysis (PCA), which reduces the dimensionality of the problem and decorrelates features.

We then used the predictions of return and risk (uncertainty) for all the assets as inputs to a Mean-Variance Optimization algorithm, which uses a quadratic solver to minimize risk for a given return. This method determines the allocation of assets, which is diverse and ensures the lowest possible level of risk, given the returns’ predictions.

3

Wealthfront

Tax minimization → offers stock-level tax-loss harvesting

Modern Portfolio Theory (MPT)

4

Preview unavailable Predict future price movements of a strategic portfolio

Liquid Alpha Program (TLAP):

TLAP seeks opportunities across global markets by identifying relationships among instruments, detecting anomolous mispricings, then structuring trades to profit from a return to normalcy. The statistical arbitrage strategy takes advantage of the idea that the market sentiment continuously overreacts, then adjusts.

5

Personalized portfolio management

Risk mitigation for concentrated stock

6

TINO IQ

identify patterns in the stocks and based on these patterns, the stocks are listed in the Tino IQ app with .

A buy and sell recommendations and estimate return

Overbought / Oversold IQ: Defining a stock as Oversold or Overbought has been done by various researchers in the past. Generally oversold stocks keep on getting oversold. We completely refreshed this approach and created smart indicators for predicting oversold/overbought stock along with a good entry point

Momentum IQ: This IQ aims to capitalize on the opportunities where there are signs of stock momentum and a stock is showing signs that momentum can continue further

Bull vs Bear Power IQ: This IQ finds those opportunities where bulls and bears have a stronger sentiment towards stock and are willing to put the money in the direction they want the stock to go on a daily basis

Money Movement IQ: This IQ aims to find opportunities where money is moving into or out of the stock

Crowd Psychology IQ: People are usually sentimental with some recent development/news in a company. This causes stocks to move excessively. This IQ tends to find if the stock is exhibiting this pattern

News IQ: We know news moves the stocks. This IQ analyzes “News” to predict the stock movement. This is a real time saver as people don’t have to spend hours everyday to read the news and think what should the stock do. Additionally we check in past how the stock had reacted to what kind of news.

Insider IQ: Insiders are known to be canary in a mine. We reverse engineer their trading patterns to find good opportunities

7

EquBot

9

WAVEBASIS

The WaveBasis platform helps investors measure, track and analyze those waves — in part through machine learning algorithms — so they know when to start trading.

Waves pattend

SIGMODIAL

https://sygnal.ai/products/

Documentation

https://docs.kaiko.com/#usage