Impact of many factors on the stock prices makes the stock prediction a difficult and highly complicated task. In this paper, machine learning techniques have been applied for the stock price prediction in order to overcome such difficulties. In the implemented work, five models have been developed and their performances are compared in predicting the stock market trends. We evaluate NiSource prediction models with Modular Neural Network (Social Media Sentiment Analysis) and Multiple Regression1,2,3,4 and conclude that the NI stock is predictable in the short/long term. According to price forecasts for (n+1 year) period: The dominant strategy among neural network is to Hold NI stock.

Keywords: NI, NiSource, stock forecast, machine learning based prediction, risk rating, buy-sell behaviour, stock analysis, target price analysis, options and futures.

## Key Points

1. Stock Forecast Based On a Predictive Algorithm
2. Market Risk
3. How do you pick a stock?

## NI Target Price Prediction Modeling Methodology

Predictions on stock market prices are a great challenge due to the fact that it is an immensely complex, chaotic and dynamic environment. There are many studies from various areas aiming to take on that challenge and Machine Learning approaches have been the focus of many of them. There are many examples of Machine Learning algorithms been able to reach satisfactory results when doing that type of prediction. This article studies the usage of LSTM networks on that scenario, to predict future trends of stock prices based on the price history, alongside with technical analysis indicators. We consider NiSource Stock Decision Process with Multiple Regression where A is the set of discrete actions of NI 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 γ ∈ [0, 1] is a move factor for expectation.1,2,3,4

F(Multiple Regression)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(Modular Neural Network (Social Media Sentiment Analysis)) X S(n):→ (n+1 year) $∑ i = 1 n s i$

n:Time series to forecast

p:Price signals of NI stock

j:Nash equilibria

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?

## NI Stock Forecast (Buy or Sell) for (n+1 year)

Sample Set: Neural Network
Stock/Index: NI NiSource
Time series to forecast n: 03 Nov 2022 for (n+1 year)

According to price forecasts for (n+1 year) period: The dominant strategy among neural network is to Hold NI 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 NiSource

1. Rebalancing does not apply if the risk management objective for a hedging relationship has changed. Instead, hedge accounting for that hedging relationship shall be discontinued (despite that an entity might designate a new hedging relationship that involves the hedging instrument or hedged item of the previous hedging relationship as described in paragraph B6.5.28).
2. To calculate the change in the value of the hedged item for the purpose of measuring hedge ineffectiveness, an entity may use a derivative that would have terms that match the critical terms of the hedged item (this is commonly referred to as a 'hypothetical derivative'), and, for example for a hedge of a forecast transaction, would be calibrated using the hedged price (or rate) level. For example, if the hedge was for a two-sided risk at the current market level, the hypothetical derivative would represent a hypothetical forward contract that is calibrated to a value of nil at the time of designation of the hedging relationship. If the hedge was for example for a one-sided risk, the hypothetical derivative would represent the intrinsic value of a hypothetical option that at the time of designation of the hedging relationship is at the money if the hedged price level is the current market level, or out of the money if the hedged price level is above (or, for a hedge of a long position, below) the current market level. Using a hypothetical derivative is one possible way of calculating the change in the value of the hedged item. The hypothetical derivative replicates the hedged item and hence results in the same outcome as if that change in value was determined by a different approach. Hence, using a 'hypothetical derivative' is not a method in its own right but a mathematical expedient that can only be used to calculate the value of the hedged item. Consequently, a 'hypothetical derivative' cannot be used to include features in the value of the hedged item that only exist in the hedging instrument (but not in the hedged item). An example is debt denominated in a foreign currency (irrespective of whether it is fixed-rate or variable-rate debt). When using a hypothetical derivative to calculate the change in the value of such debt or the present value of the cumulative change in its cash flows, the hypothetical derivative cannot simply impute a charge for exchanging different currencies even though actual derivatives under which different currencies are exchanged might include such a charge (for example, cross-currency interest rate swaps).
3. Expected credit losses are a probability-weighted estimate of credit losses (ie the present value of all cash shortfalls) over the expected life of the financial instrument. A cash shortfall is the difference between the cash flows that are due to an entity in accordance with the contract and the cash flows that the entity expects to receive. Because expected credit losses consider the amount and timing of payments, a credit loss arises even if the entity expects to be paid in full but later than when contractually due.
4. Credit risk analysis is a multifactor and holistic analysis; whether a specific factor is relevant, and its weight compared to other factors, will depend on the type of product, characteristics of the financial instruments and the borrower as well as the geographical region. An entity shall consider reasonable and supportable information that is available without undue cost or effort and that is relevant for the particular financial instrument being assessed. However, some factors or indicators may not be identifiable on an individual financial instrument level. In such a case, the factors or indicators should be assessed for appropriate portfolios, groups of portfolios or portions of a portfolio of financial instruments to determine whether the requirement in paragraph 5.5.3 for the recognition of lifetime expected credit losses has been met.

*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

NiSource assigned short-term Ba2 & long-term B2 forecasted stock rating. We evaluate the prediction models Modular Neural Network (Social Media Sentiment Analysis) with Multiple Regression1,2,3,4 and conclude that the NI stock is predictable in the short/long term. According to price forecasts for (n+1 year) period: The dominant strategy among neural network is to Hold NI stock.

### Financial State Forecast for NI NiSource Stock Options & Futures

Rating Short-Term Long-Term Senior
Outlook*Ba2B2
Operational Risk 8336
Market Risk3087
Technical Analysis8046
Fundamental Analysis8949
Risk Unsystematic6756

### Prediction Confidence Score

Trust metric by Neural Network: 91 out of 100 with 733 signals.

## References

1. M. Benaim, J. Hofbauer, and S. Sorin. Stochastic approximations and differential inclusions, Part II: Appli- cations. Mathematics of Operations Research, 31(4):673–695, 2006
2. Efron B, Hastie T, Johnstone I, Tibshirani R. 2004. Least angle regression. Ann. Stat. 32:407–99
3. V. Borkar. Stochastic approximation: a dynamical systems viewpoint. Cambridge University Press, 2008
4. K. Boda and J. Filar. Time consistent dynamic risk measures. Mathematical Methods of Operations Research, 63(1):169–186, 2006
5. Zubizarreta JR. 2015. Stable weights that balance covariates for estimation with incomplete outcome data. J. Am. Stat. Assoc. 110:910–22
6. R. Williams. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Ma- chine learning, 8(3-4):229–256, 1992
7. Bierens HJ. 1987. Kernel estimators of regression functions. In Advances in Econometrics: Fifth World Congress, Vol. 1, ed. TF Bewley, pp. 99–144. Cambridge, UK: Cambridge Univ. Press
Frequently Asked QuestionsQ: What is the prediction methodology for NI stock?
A: NI stock prediction methodology: We evaluate the prediction models Modular Neural Network (Social Media Sentiment Analysis) and Multiple Regression
Q: Is NI stock a buy or sell?
A: The dominant strategy among neural network is to Hold NI Stock.
Q: Is NiSource stock a good investment?
A: The consensus rating for NiSource is Hold and assigned short-term Ba2 & long-term B2 forecasted stock rating.
Q: What is the consensus rating of NI stock?
A: The consensus rating for NI is Hold.
Q: What is the prediction period for NI stock?
A: The prediction period for NI is (n+1 year)