Outlook: TuanChe Limited American Depositary Shares is assigned short-term Ba3 & long-term B1 estimated rating.
Dominant Strategy :
Time series to forecast n: for 6 Month
Methodology : Active Learning (ML)

## Summary

TuanChe Limited American Depositary Shares prediction model is evaluated with Active Learning (ML) and Polynomial Regression1,2,3,4 and it is concluded that the TC stock is predictable in the short/long term. Active learning (AL) is a machine learning (ML) method in which the model actively queries the user for labels on data points. This allows the model to learn more efficiently, as it is only learning about the data points that are most informative. According to price forecasts for 6 Month period, the dominant strategy among neural network is:

## Key Points

1. Prediction Modeling
2. What is Markov decision process in reinforcement learning?
3. Probability Distribution

## TC Target Price Prediction Modeling Methodology

We consider TuanChe Limited American Depositary Shares Decision Process with Active Learning (ML) where A is the set of discrete actions of TC 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(Polynomial 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(Active Learning (ML)) X S(n):→ 6 Month $\begin{array}{l}\int {r}^{s}\mathrm{rs}\end{array}$

n:Time series to forecast

p:Price signals of TC stock

j:Nash equilibria (Neural Network)

k:Dominated move

a:Best response for target price

### Active Learning (ML)

Active learning (AL) is a machine learning (ML) method in which the model actively queries the user for labels on data points. This allows the model to learn more efficiently, as it is only learning about the data points that are most informative.

### Polynomial Regression

Polynomial regression is a type of regression analysis that uses a polynomial function to model the relationship between a dependent variable and one or more independent variables. Polynomial functions are mathematical functions that have a polynomial term, which is a term that is raised to a power greater than 1. In polynomial regression, the dependent variable is modeled as a polynomial function of the independent variables. The degree of the polynomial function is determined by the researcher. The higher the degree of the polynomial function, the more complex the model will be.

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?

## TC Stock Forecast (Buy or Sell) for 6 Month

Sample Set: Neural Network
Stock/Index: TC TuanChe Limited American Depositary Shares
Time series to forecast n: for 6 Month

According to price forecasts for 6 Month period, the dominant strategy among neural network is:

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 (Grey to Black): *Technical Analysis%

## IFRS Reconciliation Adjustments for TuanChe Limited American Depositary Shares

1. An entity need not undertake an exhaustive search for information but shall consider all reasonable and supportable information that is available without undue cost or effort and that is relevant to the estimate of expected credit losses, including the effect of expected prepayments. The information used shall include factors that are specific to the borrower, general economic conditions and an assessment of both the current as well as the forecast direction of conditions at the reporting date. An entity may use various sources of data, that may be both internal (entity-specific) and external. Possible data sources include internal historical credit loss experience, internal ratings, credit loss experience of other entities and external ratings, reports and statistics. Entities that have no, or insufficient, sources of entityspecific data may use peer group experience for the comparable financial instrument (or groups of financial instruments).
2. An entity may use practical expedients when measuring expected credit losses if they are consistent with the principles in paragraph 5.5.17. An example of a practical expedient is the calculation of the expected credit losses on trade receivables using a provision matrix. The entity would use its historical credit loss experience (adjusted as appropriate in accordance with paragraphs B5.5.51–B5.5.52) for trade receivables to estimate the 12-month expected credit losses or the lifetime expected credit losses on the financial assets as relevant. A provision matrix might, for example, specify fixed provision rates depending on the number of days that a trade receivable is past due (for example, 1 per cent if not past due, 2 per cent if less than 30 days past due, 3 per cent if more than 30 days but less than 90 days past due, 20 per cent if 90–180 days past due etc). Depending on the diversity of its customer base, the entity would use appropriate groupings if its historical credit loss experience shows significantly different loss patterns for different customer segments. Examples of criteria that might be used to group assets include geographical region, product type, customer rating, collateral or trade credit insurance and type of customer (such as wholesale or retail)
3. When designating risk components as hedged items, an entity considers whether the risk components are explicitly specified in a contract (contractually specified risk components) or whether they are implicit in the fair value or the cash flows of an item of which they are a part (noncontractually specified risk components). Non-contractually specified risk components can relate to items that are not a contract (for example, forecast transactions) or contracts that do not explicitly specify the component (for example, a firm commitment that includes only one single price instead of a pricing formula that references different underlyings)
4. At the date of initial application, an entity is permitted to make the designation in paragraph 2.5 for contracts that already exist on the date but only if it designates all similar contracts. The change in the net assets resulting from such designations shall be recognised in retained earnings at the date of initial application.

*International Financial Reporting Standards (IFRS) adjustment process involves reviewing the company's financial statements and identifying any differences between the company's current accounting practices and the requirements of the IFRS. If there are any such differences, neural network makes adjustments to financial statements to bring them into compliance with the IFRS.

## Conclusions

TuanChe Limited American Depositary Shares is assigned short-term Ba3 & long-term B1 estimated rating. TuanChe Limited American Depositary Shares prediction model is evaluated with Active Learning (ML) and Polynomial Regression1,2,3,4 and it is concluded that the TC stock is predictable in the short/long term. According to price forecasts for 6 Month period, the dominant strategy among neural network is:

### TC TuanChe Limited American Depositary Shares Financial Analysis*

Rating Short-Term Long-Term Senior
Outlook*Ba3B1
Income StatementBaa2Baa2
Balance SheetBaa2C
Leverage RatiosB3Ba3
Cash FlowCaa2B2
Rates of Return and ProfitabilityBaa2Caa2

*Financial analysis is the process of evaluating a company's financial performance and position by neural network. It involves reviewing the company's financial statements, including the balance sheet, income statement, and cash flow statement, as well as other financial reports and documents.
How does neural network examine financial reports and understand financial state of the company?

### Prediction Confidence Score

Trust metric by Neural Network: 91 out of 100 with 603 signals.

## References

1. Breiman L. 1993. Better subset selection using the non-negative garotte. Tech. Rep., Univ. Calif., Berkeley
2. S. Bhatnagar, H. Prasad, and L. Prashanth. Stochastic recursive algorithms for optimization, volume 434. Springer, 2013
3. Wooldridge JM. 2010. Econometric Analysis of Cross Section and Panel Data. Cambridge, MA: MIT Press
4. S. Bhatnagar, R. Sutton, M. Ghavamzadeh, and M. Lee. Natural actor-critic algorithms. Automatica, 45(11): 2471–2482, 2009
5. R. Sutton and A. Barto. Reinforcement Learning. The MIT Press, 1998
6. J. Peters, S. Vijayakumar, and S. Schaal. Natural actor-critic. In Proceedings of the Sixteenth European Conference on Machine Learning, pages 280–291, 2005.
7. Burkov A. 2019. The Hundred-Page Machine Learning Book. Quebec City, Can.: Andriy Burkov
Frequently Asked QuestionsQ: What is the prediction methodology for TC stock?
A: TC stock prediction methodology: We evaluate the prediction models Active Learning (ML) and Polynomial Regression
Q: Is TC stock a buy or sell?
A: The dominant strategy among neural network is to Buy TC Stock.
Q: Is TuanChe Limited American Depositary Shares stock a good investment?
A: The consensus rating for TuanChe Limited American Depositary Shares is Buy and is assigned short-term Ba3 & long-term B1 estimated rating.
Q: What is the consensus rating of TC stock?
A: The consensus rating for TC is Buy.
Q: What is the prediction period for TC stock?
A: The prediction period for TC is 6 Month