Insights into customer churn prediction in telecommunications can be attained through AI/ML solutions. A large telco provider used the Engine to...
Quantification of Risks & Returns for Stock on the ASX
PI.EXCHANGE worked with a financial services company to build a predictive model in the Engine for the Client to use to quantify risks for stock on the ASX.
PI.EXCHANGE worked with a financial services company to quantify the risks and returns for stocks on the ASX.
Stock trading on stock exchanges like the ASX can be a risky asset for investment. To better understand the performance of stocks, financial services companies are looking to AI/ML to derive data-driven insights to power their customers’ investment decisions. This has resulted in AI-led methodologies and platforms gaining popularity in the investment realm.
The objective: PI.EXCHANGE worked with a financial services company (the Client) to build a predictive model in the AI & Analytics Engine for the Client to use to quantify the risks. Ultimately, the Client wants to use these new insights to help their customers make more informed and higher-performing decisions within their investment strategies.
Given the inherent challenges in quantifying the level of risk in a volatile environment, such as a stock exchange market, PI.EXCHANGE aims to provide unprecedented insights into ASX data by predicting stock volatility with a model that constructs predictive confidence intervals around stock prices, one year from the observation date for every stock on the ASX. This confidence interval will be used to quantify the expected level of return, and the probability of achieving that level of return for each instrument.
PI.EXCHANGE’s solution involves providing predictions for the volatility of stocks, to create a better understanding of the likely level of risk involved. The solution was to build a model that constructs a predictive confidence interval around the stock price one year from the observation date for every stock on the ASX and use that confidence interval to quantify the expected level return and the probability of achieving that level of return.
To prepare the data, 10 years of ASX stock price data was used to build a predictive model, to construct the desired confidence intervals. Data wrangling actions within the Engine generated 796 time-series features, encapsulating volatility of stocks, the correlation between stocks, and trends within each stock's historical prices and how these trends are correlated across all ASX instruments.
This prepared data is fed through the Engine's unique Model Recommender, where a high-performing model was selected to translate the data prepared on our platform into predictive data for future stock prices. To further manage the volatile and uncertain nature of stock prices, this predictive data was used as the mean (average) of the distribution, and an estimate of the variance of the stock's historical data together with the mean price prediction was utilized to produce a numerical confidence estimate of achieving that level of return.
Finally, this model is deployed seamlessly on our Engine along with the 796 time-series features which are automatically deployed and run on a daily basis.
"We needed an affordable yet powerful AI solution to provide predictive insights into stock volatility. The speed of delivery, the robust deployment stability and their customer services were impressive, and provided us with a competitive edge to help our clients make more informed and higher-performing investment decisions”
Results & Benefits
The model created in the Engine was designed to give a prediction about the stock price one year from the current date. Recognising that stock prices are heavily volatile, the Engine created a confidence interval of possible distribution of stock price.
Accounting for the variance of the stock’s historical data alongside the mean price prediction, the AI & Analytics Engine provided a numerical estimate of each stock achieving a certain level of return. What this implies is that the Client is now able to estimate the probability that each stock will achieve a specific percentage or more in returns, over the 1-year period.
Using the AI & Analytics Engine, the Client is able to build a repeatable collaborative ML development workflow for their data science team. The value of which extends beyond the use-case at hand, and supports a continued competitive advantage through a robust AI capability. Read on for more AI/ML industry solutions.