INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent — part 6/6

Cleaned-text code points [69865, 73737). Bibliography omitted here; source.md includes it.

Observe
1. Operations: Access and interpret market indicators such as current stock prices and historical momentum data.
2. Range: Stock’s daily adjusted closing price, historical momentum in the past k days (k = 3 in this case), etc.
3. Prompts:
- The information below provides a summary of stock price ﬂuctuations over the previous few days, which is the
"momentum" of a stock. It reﬂects the trend of a stock. Momentum is based on the idea that securities that have
performed well in the past will continue to perform well, and conversely, securities that have performed poorly will
continue to perform poorly.
4. Outputs:
- (1). The daily adjusted closing price of TSLA on {2022-10-25} is {$222.42}.
- (2). Train: On {2022-10-25}, the momentum of TSLA, indicated by the price difference between the current and the
next trading
day, is {$2.22}.
Test: On {2022-10-25}, the historical momentum of TSLA, as measured by its cumulative logarithmic returns in
the past
{3} days, was {7.05%}.
Figure 4: First section of INVESTORBENCH’s workﬂow for perceiving and processing multi-sourced information from
market environment.
Reﬂect
1. Operations:
Train: - Infer the reasoning from the retrieved memories insights for the recommended trading actions the increase or
decrease of the trading stock price.
Test: - Generate recommended trading actions. - Infer the reasoning for making such trading action.
Train & Test: - Track the memory insight IDs that contributed to the current trading decision.
2. Range: Interpretation of observed market indicators and top k insights from each layer of the long-term memory
database.
3. Prompts:
Train: Given the following information, can you explain why the ﬁnancial market ﬂuctuation from the current day to the
next day behaves like this? Summarize the reason for the decision. Y ou should provide summary information and the
IDs of the information to support your summary.
T est:Given the information, can you make an investment decision? Just summarize the reason for the decision. Consider
only the available short-term information, the mid-term information, the long-term information, and the reﬂection-term
information. Consider the momentum of the historical stock price. Also, consider how much share of the stock the
investor holds now. Y ou should provide exactly one of the following investment decisions: buy or sell. Y ou could go
with the ’hold’ option if necessary. Y ou also need to provide the IDs of the information to support your decision.
4. Outputs:
Train:
- Recommended Action Reason: The recommended trading action is ’Buy’. This can be attributed to positive market
sentiment driven by a range of favorable factors. Notably, Tesla’s strong battery supply chain, effective market
expansion plans in Germany, and its ability to maintain market strength despite potential competitive threats positively
inﬂuenced investor conﬁdence, contributing to the stock price rise.
- Reﬂected Contributed Insights IDs: {261, 278, 275, 274, 161,...}
Test:
- Trading Action: {Buy}
- Recommended Action Reason: Considering the short-term positive revenue growth, higher Model 3/Y and Model S/X
deliveries, positive free cash ﬂow, and increased cash and cash equivalents, Tesla appears to have strong ﬁnancial health.
The momentum being positive, it also encourages a risk-seeking strategy. The signiﬁcant positive signs from news such
as the imminent Q3 earnings add to the favorable view of the investment. Despite the mid-term neutral sentiment,
long-term information shows only marginal drops and the stock is still looking strong overall. These, along with positive
reﬂection-term information, form the reasoning behind the ’buy’ decision...
- Reﬂected Contributed Insights IDs: {261, 278, 275, 274, 161,...}
Figure 5: Second section of INVESTORBENCH’s workﬂow for generating trading action, reasoning and reﬂection.
2525