DocuSign Research Report

## Summary

With the advent of machine learning, numerous approaches have been proposed to forecast stock prices. Various models have been developed to date such as Recurrent Neural Networks, Long Short-Term Memory, Convolutional Neural Network sliding window, etc., but were not accurate enough. Here, the aim is to predict the price of a stock and compare the results obtained using three major algorithms namely Kalman filters, XGBoost and ARIMA. We evaluate DocuSign prediction models with Active Learning (ML) and Spearman Correlation1,2,3,4 and conclude that the DOCU stock is predictable in the short/long term. According to price forecasts for (n+4 weeks) period: The dominant strategy among neural network is to Sell DOCU stock.

## Key Points

1. Can we predict stock market using machine learning?
2. Market Risk
3. Stock Rating

## DOCU Target Price Prediction Modeling Methodology

We consider DocuSign Stock Decision Process with Active Learning (ML) where A is the set of discrete actions of DOCU stock holders, F is the set of discrete states, P : S × F × S → R is the transition probability distribution, R : S × F → R is the reaction function, and Î³ ∈ [0, 1] is a move factor for expectation.1,2,3,4

F(Spearman Correlation)5,6,7= $\begin{array}{cccc}{p}_{a1}& {p}_{a2}& \dots & {p}_{1n}\\ & ⋮\\ {p}_{j1}& {p}_{j2}& \dots & {p}_{jn}\\ & ⋮\\ {p}_{k1}& {p}_{k2}& \dots & {p}_{kn}\\ & ⋮\\ {p}_{n1}& {p}_{n2}& \dots & {p}_{nn}\end{array}$ X R(Active Learning (ML)) X S(n):→ (n+4 weeks) $∑ i = 1 n s i$

n:Time series to forecast

p:Price signals of DOCU stock

j:Nash equilibria (Neural Network)

k:Dominated move

a:Best response for target price

For further technical information as per how our model work we invite you to visit the article below:

How do AC Investment Research machine learning (predictive) algorithms actually work?

## DOCU Stock Forecast (Buy or Sell) for (n+4 weeks)

Sample Set: Neural Network
Stock/Index: DOCU DocuSign
Time series to forecast n: 18 Nov 2022 for (n+4 weeks)

According to price forecasts for (n+4 weeks) period: The dominant strategy among neural network is to Sell DOCU stock.

X axis: *Likelihood% (The higher the percentage value, the more likely the event will occur.)

Y axis: *Potential Impact% (The higher the percentage value, the more likely the price will deviate.)

Z axis (Yellow to Green): *Technical Analysis%

## Adjusted IFRS* Prediction Methods for DocuSign

1. A similar example of a non-financial item is a specific type of crude oil from a particular oil field that is priced off the relevant benchmark crude oil. If an entity sells that crude oil under a contract using a contractual pricing formula that sets the price per barrel at the benchmark crude oil price minus CU10 with a floor of CU15, the entity can designate as the hedged item the entire cash flow variability under the sales contract that is attributable to the change in the benchmark crude oil price. However, the entity cannot designate a component that is equal to the full change in the benchmark crude oil price. Hence, as long as the forward price (for each delivery) does not fall below CU25, the hedged item has the same cash flow variability as a crude oil sale at the benchmark crude oil price (or with a positive spread). However, if the forward price for any delivery falls below CU25, the hedged item has a lower cash flow variability than a crude oil sale at the benchmark crude oil price (or with a positive spread).
2. An entity is not required to restate prior periods to reflect the application of these amendments. The entity may restate prior periods if, and only if, it is possible without the use of hindsight and the restated financial statements reflect all the requirements in this Standard. If an entity does not restate prior periods, the entity shall recognise any difference between the previous carrying amount and the carrying amount at the beginning of the annual reporting period that includes the date of initial application of these amendments in the opening retained earnings (or other component of equity, as appropriate) of the annual reporting period that includes the date of initial application of these amendments.
3. An entity shall apply this Standard for annual periods beginning on or after 1 January 2018. Earlier application is permitted. If an entity elects to apply this Standard early, it must disclose that fact and apply all of the requirements in this Standard at the same time (but see also paragraphs 7.1.2, 7.2.21 and 7.3.2). It shall also, at the same time, apply the amendments in Appendix C.
4. When designating a risk component as a hedged item, the hedge accounting requirements apply to that risk component in the same way as they apply to other hedged items that are not risk components. For example, the qualifying criteria apply, including that the hedging relationship must meet the hedge effectiveness requirements, and any hedge ineffectiveness must be measured and recognised.

*International Financial Reporting Standards (IFRS) are a set of accounting rules for the financial statements of public companies that are intended to make them consistent, transparent, and easily comparable around the world.

## Conclusions

DocuSign assigned short-term B2 & long-term B3 forecasted stock rating. We evaluate the prediction models Active Learning (ML) with Spearman Correlation1,2,3,4 and conclude that the DOCU stock is predictable in the short/long term. According to price forecasts for (n+4 weeks) period: The dominant strategy among neural network is to Sell DOCU stock.

### Financial State Forecast for DOCU DocuSign Stock Options & Futures

Rating Short-Term Long-Term Senior
Outlook*B2B3
Operational Risk 6876
Market Risk4131
Technical Analysis6333
Fundamental Analysis6637
Risk Unsystematic4235

### Prediction Confidence Score

Trust metric by Neural Network: 86 out of 100 with 672 signals.

## References

1. R. Rockafellar and S. Uryasev. Optimization of conditional value-at-risk. Journal of Risk, 2:21–42, 2000.
2. M. Puterman. Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, New York, 1994.
3. K. Boda, J. Filar, Y. Lin, and L. Spanjers. Stochastic target hitting time and the problem of early retirement. Automatic Control, IEEE Transactions on, 49(3):409–419, 2004
4. A. Tamar, Y. Glassner, and S. Mannor. Policy gradients beyond expectations: Conditional value-at-risk. In AAAI, 2015
5. Barkan O. 2016. Bayesian neural word embedding. arXiv:1603.06571 [math.ST]
6. J. Ott. A Markov decision model for a surveillance application and risk-sensitive Markov decision processes. PhD thesis, Karlsruhe Institute of Technology, 2010.
7. Zeileis A, Hothorn T, Hornik K. 2008. Model-based recursive partitioning. J. Comput. Graph. Stat. 17:492–514 Zhou Z, Athey S, Wager S. 2018. Offline multi-action policy learning: generalization and optimization. arXiv:1810.04778 [stat.ML]
Frequently Asked QuestionsQ: What is the prediction methodology for DOCU stock?
A: DOCU stock prediction methodology: We evaluate the prediction models Active Learning (ML) and Spearman Correlation
Q: Is DOCU stock a buy or sell?
A: The dominant strategy among neural network is to Sell DOCU Stock.
Q: Is DocuSign stock a good investment?
A: The consensus rating for DocuSign is Sell and assigned short-term B2 & long-term B3 forecasted stock rating.
Q: What is the consensus rating of DOCU stock?
A: The consensus rating for DOCU is Sell.
Q: What is the prediction period for DOCU stock?
A: The prediction period for DOCU is (n+4 weeks)